The paper introduces VULNSCOUT-C, a compact, specialized transformer model that achieves state-of-the-art performance in C code vulnerability detection while maintaining low inference cost, making it…

This survey provides a comprehensive, practical guide to ensuring the trustworthiness of complex, autonomous agentic AI systems by focusing on safety, robustness, privacy, and system security.

QASecClaw, a multi-agent LLM system, significantly improves the accuracy of Static Application Security Testing (SAST) by using specialized LLM agents to filter out false positives, achieving an F1 sc…

ContraFix is an agentic framework that improves automated vulnerability repair by using differential runtime evidence to pinpoint the root cause of bugs, achieving state-of-the-art performance on majo…

The paper proposes a trust schema and verification framework to ensure that agent skills, which augment LLMs, are rigorously verified before deployment, thereby making human-in-the-loop oversight scal…

The paper introduces Phoenix, a training-free multi-agent framework that detects code vulnerabilities by synthesizing project-specific behavioral contracts, significantly outperforming existing method…

The paper introduces RAVEN, a Retrieval-Augmented Vulnerability Exploration Network, which uses LLM agents and RAG to automatically generate comprehensive, structured vulnerability analysis reports fo…

AgentTrust is a novel runtime safety layer that intercepts and evaluates AI agent tool calls before execution, achieving high accuracy in detecting unsafe actions across complex and obfuscated scenari…

The paper introduces Argus, a novel multi-agent framework that reorchestrates Static Application Security Testing (SAST) by integrating LLMs with existing tools to achieve superior, reliable, and cost…

SAILOR automates the construction of symbolic execution harnesses by combining static analysis and LLM-based synthesis, significantly improving the scalability and effectiveness of vulnerability disco…

The paper introduces an automated framework demonstrating that LLM system instructions are vulnerable to encoding attacks, where structured output requests can bypass safety refusals and leak sensitiv…

The paper addresses the gap in understanding real-world LLM-in-the-loop vulnerabilities by creating the LLMCVE dataset and demonstrating that these vulnerabilities are significantly harder to repair t…

AEGIS is a novel multi-agent framework that grounds vulnerability reasoning by reconstructing per-variable dependency chains over a Code Property Graph, achieving state-of-the-art performance on the P…

GoAT-X introduces a novel framework that structures cross-chain smart contract auditing as a Graph of Auditing Thoughts, significantly improving the detection of complex, semantic vulnerabilities in m…

The paper introduces a novel multi-LLM orchestration system combined with symbolic execution to successfully detect memory vulnerabilities in uncompilable, incomplete Rust CVE code snippets, achieving…

The paper introduces TRAILS~, a novel method that improves code correctness validation by grounding LLM reasoning in concrete (input, output) pairs derived from specifications, achieving state-of-the-…

The paper introduces LogicEval, a systematic framework and dataset (LogicDS) to evaluate automated repair techniques for logical software vulnerabilities, finding that prompt sensitivity and context l…

The paper introduces SecPI, a fine-tuning pipeline that teaches reasoning language models (RLMs) to autonomously internalize structured security reasoning, significantly improving secure code generati…

This study formally verified 3,500 AI-generated code artifacts and found that a majority (55.8%) contain exploitable security vulnerabilities, regardless of the LLM used.

The paper introduces SEC-bench Pro, a rigorous benchmark for evaluating LLM-based bug hunting on complex software, finding that even advanced agents struggle with long-horizon security tasks.