🔒 Language-based security - matmat · Scour

CI-Work: Benchmarking Contextual Integrity in Enterprise LLM Agents 🛡️Proof-Carrying Data

Additive Cryptography for TLS 🌐DNS Security

DCP-AI – Portable accountability layer for AI agents (post-quantum) 🌐NetworkProtocols

github.com·3d·Hacker News

No Exploit Needed: How Attackers Walk Through the Front Door via Identity-Based Attacks 🎯Threat Hunting

deadpixi/nondescript: A simple embedded programming language 🔧Binary Parsers

github.com·2d·Lobsters

An AI Agent Execution Environment to Safeguard User Data 🛡️Preservation Proofs

Reinforcing privacy reasoning in LLMs via normative simulacra from fiction 🛡️Differential Privacy

False Security Confidence in Benign LLM Code Generation 🧪CBOR Fuzzing

Towards Secure Logging: Characterizing and Benchmarking Logging Code Security Issues with LLMs ⚡Proof Automation

Understanding Secret Leakage Risks in Code LLMs: A Tokenization Perspective 💻Local LLMs

Stealthy Backdoor Attacks against LLMs Based on Natural Style Triggers 🛡️WASM Sandboxing

Making TransactionIsolation Checking Practical ✅Format Verification

Symbolic Guardrails for Domain-Specific Agents: Stronger Safety and Security Guarantees Without Sacrificing Utility 🧮Z3 Solver

Behavioral Consistency and Transparency Analysis on Large Language Model API Gateways 🌐Protocol Synthesis

Breaking Bad: Interpretability-Based Safety Audits of State-of-the-Art LLMs ⚡Proof Automation

Compositional security definitions for higher-order where declassification 🎯Dependent Preservation

SoK: Security of Autonomous LLM Agents in Agentic Commerce 🌳Archive Merkle Trees

arxiv.org·5d·Hacker News

Towards Optimal Agentic Architectures for Offensive Security Tasks 🎯Threat Hunting

Interactive Safety Verification of Distributed Protocols by Inductive Proof Decomposition 🌐Protocol Synthesis

Systematic Capability Benchmarking of Frontier Large Language Models for Offensive Cyber Tasks 🎯Threat Hunting

Log in to enable infinite scrolling