🔒 Language-based security - matmat · Scour

Reasoning Fails Where Step Flow Breaks 👑Isabelle/HOL

arxiv.org·3d

Securing AI & Agentic Applications 🛡️CLI Security

billdx.github.io·5d·Hacker News

TRUSTDESC: Preventing Tool Poisoning in LLM Applications via Trusted Description Generation ⚡Proof Automation

arxiv.org·2d

BRASP: Boolean Range Queries over Encrypted Spatial Data with Access and Search Pattern Privacy 🛡️Preservation Proofs

arxiv.org·2d

MCP-DPT: A Defense-Placement Taxonomy and Coverage Analysis for Model Context Protocol Security 🧪Protocol Fuzzing

arxiv.org·2d

Vulnerability Detection with Interprocedural Context in Multiple Languages: Assessing Effectiveness and Cost of Modern LLMs 🛡️CBOR Security

arxiv.org·2d

ARuleCon: Agentic Security Rule Conversion 🧪CBOR Fuzzing

arxiv.org·3d

Towards Identification and Intervention of Safety-Critical Parameters in Large Language Models 🔍Z3 Parsing

arxiv.org·2d

Hackers or Hallucinators? A Comprehensive Analysis of LLM-Based Automated Penetration Testing 🧪Protocol Fuzzing

arxiv.org·4d

A Formal Security Framework for MCP-Based AI Agents: Threat Taxonomy, Verification Models, and Defense Mechanisms 🔲Cellular Automata

arxiv.org·4d

PoC-Adapt: Semantic-Aware Automated Vulnerability Reproduction with LLM Multi-Agents and Reinforcement Learning-Driven Adaptive Policy 🤝Paxos Consensus

arxiv.org·3d

A Logic of Secrecy on Simplicial Models 🔲Lattice Cryptography

arxiv.org·5d

SALLIE: Safeguarding Against Latent Language & Image Exploits 🧪Binary Fuzzing

arxiv.org·3d

Probabilistic Language Tries: A Unified Framework for Compression, Decision Policies, and Execution Reuse 🧮Kolmogorov Bounds

arxiv.org·3d

LanG -- A Governance-Aware Agentic AI Platform for Unified Security Operations 🔲Cellular Automata

arxiv.org·4d

Towards Secure Agent Skills: Architecture, Threat Taxonomy, and Security Analysis 🎯Threat Hunting

arxiv.org·6d

Say Something Else: Rethinking Contextual Privacy as Information Sufficiency 🛡️Differential Privacy

arxiv.org·3d

CritBench: A Framework for Evaluating Cybersecurity Capabilities of Large Language Models in IEC 61850 Digital Substation Environments 🔐CBOR

arxiv.org·4d

From Incomplete Architecture to Quantified Risk: Multimodal LLM-Driven Security Assessment for Cyber-Physical Systems 🎯Threat Hunting

arxiv.org·4d

The Art of Building Verifiers for Computer Use Agents 🛡️Preservation Proofs

arxiv.org·3d

Loading more...