Testing

The paper introduces PickleFuzzer, a custom fuzzer that identifies security-critical discrepancies across different Python pickle implementations, finding 14 new bugs including four that could bypass…

LISA is a novel LLM-based invariant testing framework for software functional bugs, achieving higher bug-detection rates and competitive code coverage than fuzzing and prior LLM-based test generation…

This paper systematically surveys adaptive and AI-augmented security testing, concluding that a major gap exists—structural-adaptive fragmentation—where current systems fail to integrate structural pr…

This paper proposes approaches for guiding a fuzzer using feedback derived from a control-flow-graph-like structure during the fuzzing of black-box devices and obfuscated compiled binaries.

FuzzingBrain V2 is a multi-agent LLM system that significantly improves automated vulnerability discovery by ensuring all reported bugs are fuzzer-reproducible and handling complex cross-function depe…

The paper demonstrates that advanced capabilities, such as jailbreaking large language models and finding software vulnerabilities, can be achieved effectively at zero cost by coordinating multiple sm…

This paper introduces HiFuzz, a hierarchical reinforcement learning framework for processor verification that replaces mutation with a structured generation process and integrates coverage reward mech…

SDLLMFuzz is a novel dynamic-static framework that combines LLM-based structure-aware input generation with semantic feedback from crash analysis to significantly improve vulnerability discovery in st…

The paper introduces QuartetFuzz, an autonomous system that systematically ensures the correctness of fuzzing harnesses using a novel Four Principles framework, significantly improving vulnerability d…

The paper proposes a Semantic Gateway and a Zero-Trust security model to formally validate and secure autonomous AI agents operating in enterprise systems, achieving a 100% discovery rate of unauthori…

The paper introduces a verifier-fuzzing framework to detect and analyze failure modes in Reinforcement Learning with Verifiable Rewards (RLVR) where bugs in the reward verifier can be exploited by the…

The paper proposes agentic fuzzing, a novel bug-finding approach where deep agents perform direct reasoning based on historical bugs to discover logic bugs in mature codebases.

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.

AnyPoC introduces a general multi-agent framework that reliably generates and validates executable Proof-of-Concept (PoC) tests from candidate bug reports, significantly improving automated bug detect…

This paper evaluates the security of authentication code generated by five AI coding assistants using static code analysis and dynamic penetration testing, revealing inconsistent compliance with NIST…

The paper introduces FIDO, a novel framework that significantly boosts firmware fuzzing efficiency by accurately managing the timing and quantity of input delivery based on the firmware's internal inp…

Xvada introduces new techniques for deterministic context-free grammar inference, improving accuracy and compactness over existing approaches, and discovers vulnerabilities in Python Liquid engine.

This paper proposes a role-based agentic workflow for vulnerability analysis and mitigation in software engineering, integrating an analyzer agent with CodeQL and evaluating its performance on 25 real…

MemHint is a neuro-symbolic static analysis pipeline that significantly improves memory leak detection in C/C++ by combining LLM semantic understanding with Z3 symbolic reasoning, detecting more leaks…

The paper introduces VCAO, a novel verifier-centered agentic orchestration framework that models OS vulnerability discovery as a Bayesian Stackelberg game, significantly improving vulnerability discov…