7 papers
Tetrahedral linkage as an intrinsic measure of glycan antifreeze behavior
Aakash Kumar, Shoumik Saha, Dilip Gersappe
Antifreeze materials prevent ice-formation by disrupting the ice-formation by binding to certain ice-planes. Cellulose, the most abundant biopolymer, has shown the ability to bind…
Breaking the Code: Security Assessment of AI Code Agents Through Systematic Jailbreaking Attacks
Shoumik Saha, Jifan Chen, Sam Mayers +3
Code-capable large language model (LLM) agents are embedded in software engineering workflows where they can read, write, and execute code, raising "jailbreak" stakes beyond text-o…
Same Question, Different Answers: Evaluating LLM Reliability Beyond Accuracy
Kazem Faghih, Yize Cheng, Shoumik Saha +3
Large language models (LLMs) often achieve strong accuracy on benchmarks, yet it remains unclear how reliably they apply this knowledge when the same question is phrased in differe…
Under the Hood of SKILL.md: Semantic Supply-chain Attacks on AI Agent Skill Registry
Shoumik Saha, Kazem Faghih, Soheil Feizi
Autonomous AI agents increasingly extend their capabilities through Agent Skills: modular filesystem packages whose SKILL.md files describe when and how agents should use them. Whi…
Adversarial Paraphrasing: A Universal Attack for Humanizing AI-Generated Text
Yize Cheng, Vinu Sankar Sadasivan, Mehrdad Saberi +2
The increasing capabilities of Large Language Models (LLMs) have raised concerns about their misuse in AI-generated plagiarism and social engineering. While various AI-generated te…
Almost AI, Almost Human: The Challenge of Detecting AI-Polished Writing
Shoumik Saha, Soheil Feizi
The growing use of large language models (LLMs) for text generation has led to widespread concerns about AI-generated content detection. However, an overlooked challenge is AI-poli…