ARXIV:2602.18252 · ADVERSARIAL ROBUSTNESS · SUBMITTED 02 APR · 02:30 UTC · FRESHNESS STALE

VerifiedSource: PDF linkedPartialPaperPack: 3 of 4 citation fields filledMissingMissing fields: authorsPartialProof: unverified proof status

On the Adversarial Robustness of Discrete Image Tokenizers

arXiv

Exploring adversarial robustness in discrete image tokenizers to enhance multimodal system security.

Blocked on Code›Score2.0Evidence unverified

Opportunity summary

Pain Exploring adversarial robustness in discrete image tokenizers to enhance multimodal system security.

Evidence 0 refs | 0 sources | 17% coverage

Blocker Evidence unverified

Open Build Read PDF Signal Canvas Track

PROBLEM

Exploring adversarial robustness in discrete image tokenizers to enhance multimodal system security. However, unlike CLIP encoders, their vulnerability to adversarial attacks has not been explored.

METHOD

Full abstract

Discrete image tokenizers encode visual inputs as sequences of tokens from a finite vocabulary and are gaining popularity in multimodal systems, including encoder-only, encoder-decoder, and decoder-only models. However, unlike CLIP encoders, their vulnerability to adversarial attacks has not been explored. Ours being the first work studying this topic, we first formulate attacks that aim to perturb the features extracted by discrete tokenizers, and thus change the extracted tokens. These attacks are computationally efficient, application-agnostic, and effective across classification, multimodal retrieval, and captioning tasks. Second, to defend against this vulnerability, inspired by recent work on robust CLIP encoders, we fine-tune popular tokenizers with unsupervised adversarial training, keeping all other components frozen. While unsupervised and task-agnostic, our approach significantly improves robustness to both unsupervised and end-to-end supervised attacks and generalizes well to unseen tasks and data. Unlike supervised adversarial training, our approach can leverage unlabeled images, making it more versatile. Overall, our work highlights the critical role of tokenizer robustness in downstream tasks and presents an important step in the development of safe multimodal foundation models.

RESULT

ScienceToStartup currently rates this 2.0/10 on the public viability pass. While unsupervised and task-agnostic, our approach significantly improves robustness to both unsupervised and end-to-end supervised attacks and generalizes well to unseen tasks and data.

WHY NOW

Adversarial Robustness moved forward this cycle; last verified April 2026. Public score 2.0/10.

Continue into Read for claims, analysis, references, and neighboring papers.

Opportunity summary

Score2.0

PainExploring adversarial robustness in discrete image tokenizers to enhance multimodal system security.

Evidence0 refs | 0 sources | 17% coverage

Blockermissing authors

Analysis summary

Exploring adversarial robustness in discrete image tokenizers to enhance multimodal system security.

VerifiedSource: PDF linkedPartialPaperPack: 3 of 4 citation fields filledMissingMissing fields: authorsPartialProof: unverified proof status

ARXIV:2602.18252 · ADVERSARIAL ROBUSTNESS · SUBMITTED 02 APR · 02:30 UTC · FRESHNESS STALE

VerifiedSource: PDF linkedPartialPaperPack: 3 of 4 citation fields filledMissingMissing fields: authorsPartialProof: unverified proof status

On the Adversarial Robustness of Discrete Image Tokenizers

arXiv

Exploring adversarial robustness in discrete image tokenizers to enhance multimodal system security.

Blocked on Code›Score2.0Evidence unverified

Opportunity summary

Pain Exploring adversarial robustness in discrete image tokenizers to enhance multimodal system security.

Evidence 0 refs | 0 sources | 17% coverage

Blocker Evidence unverified

Open Build Read PDF Signal Canvas Track

PROBLEM

Exploring adversarial robustness in discrete image tokenizers to enhance multimodal system security. However, unlike CLIP encoders, their vulnerability to adversarial attacks has not been explored.

METHOD

Full abstract

RESULT

WHY NOW

Adversarial Robustness moved forward this cycle; last verified April 2026. Public score 2.0/10.

Continue into Read for claims, analysis, references, and neighboring papers.

Opportunity summary

Score2.0

PainExploring adversarial robustness in discrete image tokenizers to enhance multimodal system security.

Evidence0 refs | 0 sources | 17% coverage

Blockermissing authors

Analysis summary

Exploring adversarial robustness in discrete image tokenizers to enhance multimodal system security.

VerifiedSource: PDF linkedPartialPaperPack: 3 of 4 citation fields filledMissingMissing fields: authorsPartialProof: unverified proof status

Paper Pack

10.48550/arXiv.2602.18252

On the Adversarial Robustness of Discrete Image Tokenizers

Exploring adversarial robustness in discrete image tokenizers to enhance multimodal system security.

Abstract

Source availability

PDF linked

The paper record includes a public PDF URL.

Extraction status

Derived fallback

Read summaries are estimated from adjacent metadata, not verified extraction rows.

Proof status

unverified

0 refs; 0 sources; 17% coverage.

What was readable

linkedon filenot materializedderived fallback40 indexednot indexed

Derived fallback: Estimated from adjacent evidence; not verified from source.

Viability

2.0

Time to MVP

MVP estimate missing

Commercial

No commercial flags on file

Export

Preparing verified analysis

lens / founder

PROBLEM

Exploring adversarial robustness in discrete image tokenizers to enhance multimodal system security. However, unlike CLIP encoders, their vulnerability to adversarial attacks has not been explored.

METHOD

RESULT

WHY NOW

Adversarial Robustness moved forward this cycle; last verified April 2026. Public score 2.0/10.

Claim map

Abstract-backed public claims while anchored extraction refreshes.

Strong 0Mixed 0Weak 4

Evidencepartial
Exploring adversarial robustness in discrete image tokenizers to enhance multimodal system security. However, unlike CLIP encoders, their vulnerability to adversarial attacks has not been explored.
Implicationpartial
Abstract-backed fallback claim; anchored extraction has not materialized a public claim row yet.
Verificationpartial
partial
Evidencepartial
Discrete image tokenizers encode visual inputs as sequences of tokens from a finite vocabulary and are gaining popularity in multimodal systems, including encoder-only, encoder-decoder, and decoder-only models. However, unlike CLIP encoders, their vulnerability to adversarial attacks has not been explored.
Implicationpartial
Abstract-backed fallback claim; anchored extraction has not materialized a public claim row yet.
Verificationpartial
partial
Evidencepartial
ScienceToStartup currently rates this 2.0/10 on the public viability pass. While unsupervised and task-agnostic, our approach significantly improves robustness to both unsupervised and end-to-end supervised attacks and generalizes well to unseen tasks and data.
Implicationpartial
Abstract-backed fallback claim; anchored extraction has not materialized a public claim row yet.
Verificationpartial
partial
Evidencepartial
Adversarial Robustness moved forward this cycle; last verified April 2026. Public score 2.0/10.
Implicationpartial
Abstract-backed fallback claim; anchored extraction has not materialized a public claim row yet.
Verificationpartial
partial

Constellation map

Paper-native neighborhood for concepts, methods, materials, markets, and competitors. Missing lanes stay labeled instead of disappearing behind commercialization gates.

Open full Signal Canvas

Concepts

not indexed

Methods

Materials

PDF linked

Markets

Adversarial Robustness

Competitors

not indexed

Competitive landscape

Exploring adversarial robustness in discrete image tokenizers to enhance multimodal system security.

Segment

Adversarial Robustness

Adoption evidence

No public code link in the paper record yet

Commercial read

2.0/10 public viability

Direct

not classified

Adjacent

not classified

Substitute

not classified

Unknown

not classified

Buzz

No indexed public discussion is attached to 2602.18252 yet. That is a visibility signal, not a blank module: the monitor is watching the public channels below.

Hacker News

Not indexed yet

Bluesky

Not indexed yet

PDF

Preview the source document here, or use the hero PDF action for a new tab.

References(40)

FuseLIP: Multimodal Embeddings via Early Fusion of Discrete Tokens

2025Christian Schlarmann, Francesco Croce et al.

Selftok: Discrete Visual Tokens of Autoregression, by Diffusion, and for Reasoning

2025Bohan Wang, Zhongqi Yue et al.

Unified Autoregressive Visual Generation and Understanding with Continuous Tokens

2025Lijie Fan, Luming Tang et al.

UniTok: A Unified Tokenizer for Visual Generation and Understanding

2025Chuofan Ma, Yi Jiang et al.

FlexTok: Resampling Images into 1D Token Sequences of Flexible Length

2025Roman Bachmann, Jesse Allardice et al.

One-D-Piece: Image Tokenizer Meets Quality-Controllable Compression

2025Keita Miwa, Kento Sasaki et al.

Emu3: Next-Token Prediction is All You Need

2024Xinlong Wang, Xiaosong Zhang et al.

Show-o: One Single Transformer to Unify Multimodal Understanding and Generation

2024Jinheng Xie, Weijia Mao et al.

LLaVA-NeXT-Interleave: Tackling Multi-image, Video, and 3D in Large Multimodal Models

2024Feng Li, Renrui Zhang et al.

4M-21: An Any-to-Any Vision Model for Tens of Tasks and Modalities

2024Roman Bachmann, Ouguzhan Fatih Kar et al.

An Image is Worth 32 Tokens for Reconstruction and Generation

2024Qihang Yu, Mark Weber et al.

Chameleon: Mixed-Modal Early-Fusion Foundation Models

2024Chameleon Team, Mingda Chen et al.

Improving Adversarial Robustness in Vision-Language Models with Architecture and Prompt Design

2024Rishika Bhagwatkar, Shravan Nayak et al.

4M: Massively Multimodal Masked Modeling

2023David Mizrahi, Roman Bachmann et al.

Segment (Almost) Nothing: Prompt-Agnostic Adversarial Attacks on Segmentation Models

2023Francesco Croce, Matthias Hein

Language Model Beats Diffusion -- Tokenizer is Key to Visual Generation

2023Lijun Yu, José Lezama et al.

Finite Scalar Quantization: VQ-VAE Made Simple

2023Fabian Mentzer, David C. Minnen et al.

On the Adversarial Robustness of Multi-Modal Foundation Models

2023Christian Schlarmann, Matthias Hein

Towards Reliable Evaluation and Fast Training of Robust Semantic Segmentation Models

2023Francesco Croce, N. Singh et al.

Visual Adversarial Examples Jailbreak Aligned Large Language Models

2023Xiangyu Qi, Kaixuan Huang et al.

Showing 20 of 40 references

CITED BY

No citing papers are indexed in the public S2S graph yet. This is an explicit zero-signal state, not a hidden lookup.

Foundation

Prior WorkUnveiling the Fragility of Vision-Language Models: Multi-Modal Adversarial Synergy via Texture-Constrained Perturbations and Cross-Modal Optimization

2.0

Extension

Builds On ThisBeyond Waveform Robustness: Robust Feature-Vocoder Adversarial Attacks on Automatic Speech Recognition

0.0

Commercially relevant

Higher ViabilityBeyond Standard Benchmarks: A Systematic Audit of Vision-Language Model's Robustness to Natural Semantic Variation Across Diverse Tasks

4.0

Higher ViabilityHierarchically Robust Zero-shot Vision-language Models

4.0

Higher ViabilityMake Anything Match Your Target: Universal Adversarial Perturbations against Closed-Source MLLMs via Multi-Crop Routed Meta Optimization

3.0

Higher ViabilityAdversarial Attacks on Multimodal Large Language Models: A Comprehensive Survey

3.0

Higher ViabilityEfficient Preemptive Robustification with Image Sharpening

4.0

Higher ViabilityRobustness of Vision Language Models Against Split-Image Harmful Input Attacks

5.0

Higher ViabilitySTRAP-ViT: Segregated Tokens with Randomized -- Transformations for Defense against Adversarial Patches in ViTs

7.0

Higher ViabilityExploring Token-Space Manipulation in Latent Audio Tokenizers

4.0

Conflicting

none indexed

Related Resources

adversarial robustness(glossary)

Owned Distribution

Subscribe to the weekly brief

Get the weekly shortlist of commercializable papers, benchmark movers, and proof receipts that matter for product execution.

Agent drawer

5 surfaces preserved for agents. Humans can ignore.

Developer contracts, payload previews, evidence maps, and run controls stay here instead of the Read, Build, and Track workspace.

Run context

Paper: 2602.18252
Route: /paper/on-the-adversarial-robustness-of-discrete-image-tokenizers
Active tab: read
Artifact: on-the-adversarial-robustness-of-discrete-image-tokenizers

Available agents

Read extractor
Build planner
Track monitor
Competitive mapper
Related-paper scout

API/MCP endpoints

REST paper pack API/api/v1/paper/on-the-adversarial-robustness-of-discrete-image-tokenizers/paper-pack
REST build passport API/api/v1/paper/on-the-adversarial-robustness-of-discrete-image-tokenizers/build-passport
REST OpenAPI/api/openapi.json
MCP descriptor/api/mcp
MCP resourcesciencetostartup://surfaces/paper-workspace

Tool contracts

paper_packbuild_passportopportunity_kernelforesightsource_proofevidence_state

Payload preview

Inspect payload

{
  "contract_version": "paper-r2",
  "paper_id": "ffdf41d5-a2b7-4486-a539-fca8368d64b8",
  "arxiv_id": "2602.18252",
  "canonical_route": "/paper/on-the-adversarial-robustness-of-discrete-image-tokenizers",
  "active_tab": "synced from current hash by the drawer client",
  "selected_artifact": "on-the-adversarial-robustness-of-discrete-image-tokenizers",
  "endpoints": {
    "paper_pack": "/api/v1/paper/on-the-adversarial-robustness-of-discrete-image-tokenizers/paper-pack",
    "build_passport": "/api/v1/paper/on-the-adversarial-robustness-of-discrete-image-tokenizers/build-passport",
    "mcp_resource": "sciencetostartup://surfaces/paper-workspace"
  }
}

Schema validation

paper-r2 contract: present
JSON-LD twin: SSR emitted
OpenAPI path parity: /api/openapi.json
MCP resource parity: paper-workspace

Job trace

queued: drawer opened by user action
running: inspect or copy payload
succeeded: payload available in SSR
failed: route errors appear in evidence cards

Evidence map

sources used: page freshness, source proof anchors, JSON-LD
missing sources: exposed by PaperPack and EvidenceState chips
derived fallbacks: marked unverified before handoff

Page Freshness

Canonical route, proof status, last verified, refs, sources, and coverage.

Page Freshness

Paper proof surface

Canonical route: /paper/on-the-adversarial-robustness-of-discrete-image-tokenizers

stale

Proof freshness: stale
Proof status: unverified
Display score: 2/10
Last proof check: 2026-04-02
Score updated: 2026-04-02
Score fresh until: 2026-05-02
References: 0
Source count: 0
Coverage: 17%

This page is showing the last landed evidence receipt and score bundle because the latest proof data is outside the freshness window.

OpenAlex: pending — this preprint is not yet indexed by OpenAlex.

Agent Handoff

Endpoint list, payload shape, route context, and copyable handoff data.

Agent Handoff

On the Adversarial Robustness of Discrete Image Tokenizers

Canonical ID on-the-adversarial-robustness-of-discrete-image-tokenizers | Route /paper/on-the-adversarial-robustness-of-discrete-image-tokenizers

REST example

curl https://sciencetostartup.com/api/v1/agent-handoff/paper/on-the-adversarial-robustness-of-discrete-image-tokenizers

MCP example

{
  "tool": "get_paper",
  "arguments": {
    "arxiv_id": "2602.18252"
  }
}

source_context

{
  "surface": "paper",
  "mode": "paper",
  "query": "On the Adversarial Robustness of Discrete Image Tokenizers",
  "normalized_query": "2602.18252",
  "route": "/paper/on-the-adversarial-robustness-of-discrete-image-tokenizers",
  "paper_ref": "on-the-adversarial-robustness-of-discrete-image-tokenizers",
  "topic_slug": null,
  "benchmark_ref": null,
  "dataset_ref": null
}

Buildability Receipt

Verdict, compute envelope, blockers, signature state, and receipt links.

Paper proof page receipt window

Not build-ready: On the Adversarial Robustness of Discrete Image Tokenizers

/buildability/on-the-adversarial-robustness-of-discrete-image-tokenizers

Ignoreblocked

Subject: On the Adversarial Robustness of Discrete Image Tokenizers

Verdict

Ignore

Verdict is Ignore because current viability and proof state do not clear the buildability gate.

Time to first demo

Insufficient data

No first-demo timestamp, owner estimate, or elapsed demo receipt is attached to this surface.

Compute envelope

Structured compute envelope

Insufficient data

No data, compute, hardware, memory, latency, dependency, or serving requirement receipt is attached.

Evidence ids

Receipt path

/buildability/on-the-adversarial-robustness-of-discrete-image-tokenizers

Paper ref

on-the-adversarial-robustness-of-discrete-image-tokenizers

arXiv id

2602.18252

Freshness

Generated at

2026-04-02T02:30:40.136Z

Evidence freshness

stale

Last verification

2026-04-02T02:30:40.136Z

Sources

References

Coverage

17%

Hash state

Lineage hash

7752f80b2b76828c2be64943cfd6f38e0f96ceb0df386163cc93899700997b49

Canonical opportunity-kernel lineage hash.

Signature state

External signature

unsigned_external

No founder, registry, pilot, or production-adoption signature is attached to this receipt.

Verification

not_verified

Verification is blocked until an external signature is provided.

Blockers

Missing: repo_url
Missing: references
Missing: proof_status
Missing: distribution_readiness_scores
Missing: paper_extraction_scorecards
Unknown: distribution readiness has not been computed yet
Unknown: proof verification has not been recorded yet

Verification pending / evidence receipt incomplete

repo_url

references

Missing proof, requirement, signature, approval, adoption, or telemetry fields are blockers and must not be inferred.

Open receipt API receipt Build Loop Signal Canvas Proof divergence Divergence API Brier outcomes API

Source Proof anchors

Visual citations from the paper document graph.

JSON-LD twin

The application/ld+json payload rendered for agents.

{
  "@context": "https://schema.org",
  "@graph": [
    {
      "@type": "WebPage",
      "@id": "https://sciencetostartup.com/paper/on-the-adversarial-robustness-of-discrete-image-tokenizers#webpage",
      "url": "https://sciencetostartup.com/paper/on-the-adversarial-robustness-of-discrete-image-tokenizers",
      "name": "On the Adversarial Robustness of Discrete Image Tokenizers",
      "description": "Exploring adversarial robustness in discrete image tokenizers to enhance multimodal system security.",
      "isPartOf": {
        "@id": "https://sciencetostartup.com/#website"
      }
    },
    {
      "@type": "ScholarlyArticle",
      "@id": "https://sciencetostartup.com/paper/on-the-adversarial-robustness-of-discrete-image-tokenizers#scholarlyArticle",
      "headline": "On the Adversarial Robustness of Discrete Image Tokenizers",
      "description": "Exploring adversarial robustness in discrete image tokenizers to enhance multimodal system security.",
      "url": "https://sciencetostartup.com/paper/on-the-adversarial-robustness-of-discrete-image-tokenizers",
      "sameAs": "https://arxiv.org/abs/2602.18252",
      "identifier": {
        "@type": "PropertyValue",
        "propertyID": "arXiv",
        "value": "2602.18252"
      },
      "isAccessibleForFree": true,
      "isPartOf": {
        "@id": "https://sciencetostartup.com/#website"
      },
      "datePublished": "2026-02-20T14:39:17.000Z",
      "citation": [
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "5324fb2280cd350dbc3ca1261d1b1ac69811de05"
          },
          "url": "https://www.semanticscholar.org/paper/5324fb2280cd350dbc3ca1261d1b1ac69811de05"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "370869e0978b27f496008cd434e2b00f8bea93de"
          },
          "url": "https://www.semanticscholar.org/paper/370869e0978b27f496008cd434e2b00f8bea93de"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "b65f7e95303383a418a6c7c510fcbdb7f91c9d54"
          },
          "url": "https://www.semanticscholar.org/paper/b65f7e95303383a418a6c7c510fcbdb7f91c9d54"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "289d46628d721374535e8e4b45abd7408249cda7"
          },
          "url": "https://www.semanticscholar.org/paper/289d46628d721374535e8e4b45abd7408249cda7"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "a3ebbaabc51e6f666802bcbccc149027bdc9f5a9"
          },
          "url": "https://www.semanticscholar.org/paper/a3ebbaabc51e6f666802bcbccc149027bdc9f5a9"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "829ecf5fa63497e95b7ae8dd6e60d989685dea92"
          },
          "url": "https://www.semanticscholar.org/paper/829ecf5fa63497e95b7ae8dd6e60d989685dea92"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "3281d5a46c9de4f7d80c28f58f3aea03e445bd0a"
          },
          "url": "https://www.semanticscholar.org/paper/3281d5a46c9de4f7d80c28f58f3aea03e445bd0a"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "9dc337bd18bc0201839942931b12aff8ec1c93f5"
          },
          "url": "https://www.semanticscholar.org/paper/9dc337bd18bc0201839942931b12aff8ec1c93f5"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "2e230519ef242e592b3c19765639008c7046424f"
          },
          "url": "https://www.semanticscholar.org/paper/2e230519ef242e592b3c19765639008c7046424f"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "4b1655a321392d0fadcf25ef5bd4040123e33244"
          },
          "url": "https://www.semanticscholar.org/paper/4b1655a321392d0fadcf25ef5bd4040123e33244"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "1e31f4a4ccfc0d1e461be05361d77b5e045f4d37"
          },
          "url": "https://www.semanticscholar.org/paper/1e31f4a4ccfc0d1e461be05361d77b5e045f4d37"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "32112b798f70faab00e14806f51d46058cf5e597"
          },
          "url": "https://www.semanticscholar.org/paper/32112b798f70faab00e14806f51d46058cf5e597"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "13925d7d5952b1ba5960dfe2c44d977be109b636"
          },
          "url": "https://www.semanticscholar.org/paper/13925d7d5952b1ba5960dfe2c44d977be109b636"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "2b967c5b855497a8f9de829fafc36c250e1dbbaf"
          },
          "url": "https://www.semanticscholar.org/paper/2b967c5b855497a8f9de829fafc36c250e1dbbaf"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "985f0c89c5a607742ec43c1fdc2cbfe54541cbad"
          },
          "url": "https://www.semanticscholar.org/paper/985f0c89c5a607742ec43c1fdc2cbfe54541cbad"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "eb76781932d4cdc241f1d739f7a6e3d34a4eec87"
          },
          "url": "https://www.semanticscholar.org/paper/eb76781932d4cdc241f1d739f7a6e3d34a4eec87"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "5690e35b8beab92a80055fe2530c29c24e495379"
          },
          "url": "https://www.semanticscholar.org/paper/5690e35b8beab92a80055fe2530c29c24e495379"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "b6a7b7005322d19ab081e9007b71b41b57743671"
          },
          "url": "https://www.semanticscholar.org/paper/b6a7b7005322d19ab081e9007b71b41b57743671"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "142e934dd5d6c53f877c30243d436255e3a0dde7"
          },
          "url": "https://www.semanticscholar.org/paper/142e934dd5d6c53f877c30243d436255e3a0dde7"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "d3fecc974f8a6a39e6f0436057e75de0b810aecd"
          },
          "url": "https://www.semanticscholar.org/paper/d3fecc974f8a6a39e6f0436057e75de0b810aecd"
        }
      ],
      "additionalProperty": [
        {
          "@type": "PropertyValue",
          "propertyID": "viabilityScore",
          "value": 2
        },
        {
          "@type": "PropertyValue",
          "propertyID": "researchDomain",
          "value": "Adversarial Robustness"
        }
      ]
    },
    {
      "@type": "BreadcrumbList",
      "itemListElement": [
        {
          "@type": "ListItem",
          "position": 1,
          "name": "Home",
          "item": "https://sciencetostartup.com"
        },
        {
          "@type": "ListItem",
          "position": 2,
          "name": "Adversarial Robustness",
          "item": "https://sciencetostartup.com/topics"
        },
        {
          "@type": "ListItem",
          "position": 3,
          "name": "On the Adversarial Robustness of Discrete Image Tokenizers",
          "item": "https://sciencetostartup.com/paper/on-the-adversarial-robustness-of-discrete-image-tokenizers"
        }
      ]
    }
  ]
}

On the Adversarial Robustness of Discrete Image Tokenizers

On the Adversarial Robustness of Discrete Image Tokenizers

Claim map

Constellation map

Competitive landscape

Buzz

PDF

References(40)

Related Papers

Related Resources

Subscribe to the weekly brief

Build artifacts

Brief

Experiment plan

Validation checklist

Scientific founder

Translational engineer

Domain operator

GTM lead

Regulatory/clinical advisor

Timeline

Claim map

Constellation map

Competitive landscape

Buzz

PDF

References(40)

Related Papers

Related Resources

Subscribe to the weekly brief

Build artifacts

Brief

Experiment plan

Validation checklist

Scientific founder

Translational engineer

Domain operator

GTM lead

Regulatory/clinical advisor

Timeline