arXiv AI
Measuring and Exploiting Contextual Bias in LLM-Assisted Security Code Review
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
arXiv AI
Jun 30
Words Speak Louder Than Code: Investigating Cognitive Heuristics in LLM-Based Code Vulnerability Detection
arXiv:2606. 30587v1 Announce Type: cross Abstract: Researchers and practitioners increasingly apply Large Language Models (LLMs) for automated vulnerability detection.
arXiv AI
Jun 18
Code-Augur: Agentic Vulnerability Detection via Specification Inference
arXiv:2606. 18619v1 Announce Type: cross Abstract: The advent of agentic vulnerability detection is already becoming a watershed moment for software security.
arXiv AI
Aug 18
Workspace Topology as an Attack Vector in Agentic Coding Assistants
arXiv:2608. 14876v1 Announce Type: cross Abstract: Agentic coding assistants are finding widespread use, not just in new code development but in quickly ingesting and leveraging third-party code.
arXiv Machine Learning
Sep 3
CodePoisonRAG: Knowledge Poisoning Attacks on Retrieval-Augmented Code Generation
The paper introduces CodePoisonRAG, a framework that poisons retrieval-augmented code generation systems by transforming benign code artifacts into malicious ones. It injects CWE-specific vulnerabilities and false safety claims into a single task-matched artifact, achieving high success rates across multiple generators and even against a defense system. The study demonstrates that attackers can target and propagate specific weaknesses without altering the underlying language model.
arXiv AI
Jul 28
Poster: Rethinking Security in LLM Code Generation through Real-World Risk Scenarios
arXiv:2607. 23088v1 Announce Type: cross Abstract: Large Language Models (LLMs) are widely used for code generation, yet their security behavior in realistic development workflows remains underexplored.
arXiv AI
Jun 15
SEVRA-BENCH: Social Engineering of Vulnerabilities in Review Agents
arXiv:2606. 13757v1 Announce Type: cross Abstract: Large language model (LLM) reviewers are increasingly used in pull-request (PR) workflows, where their approvals help decide which code is merged into a repository.