5 papers
From Documentation to Zero-day Vulnerabilities: LLM-Driven Fuzzing of JavaScript Engines in PDF Readers
Suyue Guo, Stijn Pletinckx, Tianle Yu +5
Existing fuzzers for PDF readers rely on simple test cases that involve only individual API calls, leading to limited coverage and potentially missing vulnerabilities that require…
In-Context Watermarks for Large Language Models
Yepeng Liu, Xuandong Zhao, Christopher Kruegel +2
The growing use of large language models (LLMs) for sensitive applications has highlighted the need for effective watermarking techniques to ensure the provenance and accountabilit…
DevOps-Gym: Benchmarking AI Agents in Software DevOps Cycle
Yuheng Tang, Kaijie Zhu, Bonan Ruan +14
Even though demonstrating extraordinary capabilities in code generation and software issue resolving, AI agents' capabilities in the full software DevOps cycle are still unknown. D…
Multi-Agent Taint Specification Extraction for Vulnerability Detection
Jonah Ghebremichael, Saastha Vasan, Saad Ullah +6
Static Application Security Testing (SAST) tools using taint analysis are widely viewed as providing higher-quality vulnerability detection results compared to traditional pattern-…
When AI Meets the Web: Prompt Injection Risks in Third-Party AI Chatbot Plugins
Yigitcan Kaya, Anton Landerer, Stijn Pletinckx +3
Prompt injection attacks pose a critical threat to large language models (LLMs), with prior work focusing on cutting-edge LLM applications like personal copilots. In contrast, simp…