PrimeVul
PulseAugur coverage of PrimeVul — every cluster mentioning PrimeVul across labs, papers, and developer communities, ranked by signal.
1 day(s) with sentiment data
-
LLMs show asymmetric deference to static analysis evidence in vulnerability detection
A new arXiv paper investigates how large language models (LLMs) interact with static analysis tools for vulnerability detection. The study found that LLMs exhibit asymmetric deference, being significantly misled by fabr…
-
AI system REVA detects code vulnerabilities in real-time
Researchers have developed REVA, a new AI system designed for real-time vulnerability detection in code. Unlike slower agent-based methods that mimic human security experts, REVA processes code functions in a single for…
-
LLM internal states reveal code vulnerabilities, study finds
Researchers have developed a method to detect code vulnerabilities by analyzing the internal activations of large language models (LLMs) rather than just their final output. By training small probes on the latent activa…
-
New benchmark IoTVulBench improves IoT firmware vulnerability detection
Researchers have introduced IoTVulBench, a new benchmark designed to improve the detection of vulnerabilities in IoT firmware. This benchmark features human-verified and contamination-screened annotations, addressing li…
-
ANVIL uses LLMs for anomaly-based vulnerability detection
Researchers have developed ANVIL, a novel approach to identifying software vulnerabilities by reframing the problem as anomaly detection. Unlike traditional supervised methods that struggle with limited labeled data, AN…
-
VulnAgent-R2 framework enhances repository-level software vulnerability detection
Researchers have developed VulnAgent-R2, an advanced multi-agent auditing framework designed to detect software vulnerabilities at the repository level. This system improves upon previous methods by incorporating module…