Proof pending. Core topic summary fields are still materializing.
The field of security is increasingly focused on addressing vulnerabilities in emerging technologies, particularly those involving large language models, federated learning, and agentic systems. Recent advancements have introduced frameworks like MCPThreatHive and ShieldNet, which automate threat intelligence and detect supply-chain injections, respectively. Additionally, research on data leakage in machine learning models and the effectiveness of new CAPTCHA systems highlights the need for robust defenses against sophisticated attacks. As threats evolve, understanding and mitigating risks associated with these technologies is crucial for developers and organizations to safeguard sensitive data and maintain system integrity. The ongoing development of post-quantum cryptography and the evaluation of security frameworks further emphasize the importance of adapting to new challenges in the security landscape.
The rapid proliferation of Model Context Protocol (MCP)-based agentic systems has introduced a new category of security threats that existing frameworks are inadequately equipped to address. We presen...
Searchable Symmetric Encryption (SSE) allows users to search over encrypted data stored on untrusted servers, like cloud providers. While SSE hides the content of queries and documents, it still leaks...
Website fingerprinting (WF) attacks on Tor can infer user destinations from encrypted traffic metadata. However, their real-world effectiveness remains debated due to laboratory settings that fail to ...
Advances in quantum computing threaten digital communication security by undermining the foundations of current public-key cryptography through Shor's quantum algorithm. This has driven the developmen...
Existing research on LLM agent security mainly focuses on prompt injection and unsafe input/output behaviors. However, as agents increasingly rely on third-party tools and MCP servers, a new class of ...
Transaction processing systems underpin modern commerce, finance, and critical infrastructure, yet their security has never been studied across the full evolutionary arc of these systems. Over five de...
Machine learning models are increasingly used for software security tasks. These models are commonly trained and evaluated on large Internet-derived datasets, which often contain duplicated or highly ...
The rapid evolution of GUI-enabled agents has rendered traditional CAPTCHAs obsolete. While previous benchmarks like OpenCaptchaWorld established a baseline for evaluating multimodal agents, recent ad...
Graph Neural Networks (GNNs) have achieved remarkable results in various tasks. Recent studies reveal that graph backdoor attacks can poison the GNN model to predict test nodes with triggers attached ...
Multimodal Large Language Models (MLLMs) integrate vision and text to power applications, but this integration introduces new vulnerabilities. We study Image-based Prompt Injection (IPI), a black-box ...
Freshness
Canonical route: /topics
Agent Handoff
Canonical ID security | Route /topic/security
REST example
curl https://sciencetostartup.com/api/v1/agent-handoff/topic/securityMCP example
{
"tool": "search_papers",
"arguments": {
"query": "Security",
"cluster": "Security"
}
}source_context
{
"surface": "topic",
"mode": "topic",
"query": "Security",
"normalized_query": "security",
"route": "/topic/security",
"paper_ref": null,
"topic_slug": "security",
"benchmark_ref": null,
"dataset_ref": null
}Use This Via API or MCP
Topic pages bundle paper counts, viability trends, author concentration, and top questions into one canonical surface your agents can reference before they open Signal Canvas or create a workspace.