Somesh Jha

ATLAS: Constraints-Aware Multi-Agent Collaboration for Real-World Travel Planning

ARMOR: Aligning Secure and Safe Large Language Models via Meticulous Reasoning

Through the Stealth Lens: Attention-Aware Defenses Against Poisoning in RAG

Auto-SPT: Automating Semantic Preserving Transformations for Code

LLM-Based Code Translation Needs Formal Compositional Reasoning

AutoDAN-Turbo: A Lifelong Agent for Strategy Self-Exploration to Jailbreak LLMs

Functional Homotopy: Smoothing Discrete Optimization via Continuous Parameters for LLM Jailbreak Attacks

What Really is a Member? Discrediting Membership Inference via Poisoning

Can Watermarks be Used to Detect LLM IP Infringement For Free?

CONDA: Adaptive Concept Bottleneck for Foundation Models Under Distribution Shifts

Validating Mechanistic Interpretations: An Axiomatic Approach

AutoHijacker: Automatic Indirect Prompt Injection Against Black-box LLM Agents