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
Oct 28
When AI Agrees Too Much: Manipulating Automated Code Review via Bias Injection
The paper investigates how large language model (LLM)–based automated code review (ACR) systems can be manipulated through contextual bias injection, a framing effect that lets presentation override content. A large‑scale study across six LLMs confirms the framing effect in vulnerability detection, and a realistic experiment on 33 CVEs in 20 projects shows that a novel LLM‑assisted refinement attack succeeds in 97% of cases, while a template‑based attack fails. The results underscore the vulnerability of real‑world ACR pipelines and the need for human oversight and trust in the development process.
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
2d ago
A.S.E 2.0: Understanding How Repository Context Impacts the Security of LLM-Generated Code
The paper introduces CASE-Bench, a benchmark of 145 repository-level tasks derived from real CVEs across 51 projects, each run in Docker with functional tests and proof‑of‑concept exploits. It evaluates 13 context‑construction methods and six controls across six LLMs, showing that functionality‑oriented context improves functional pass rates by up to 8.2 pp but only 3.7 pp for security, that omitting safeguards can drop secure pass rates by 8.1 pp, and that coding agents see relevant safeguards in only 27‑36 % of trajectories. These results highlight how repository context shapes the security of LLM‑generated code and guide the design of security‑aware context construction and evaluation.
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.