17 papers
Code Monitor Red Teaming for Public-Test-Passing Code
Junchi Liao, Jiawen Deng, Fuji Ren
Visible tests are a common gate for LLM-generated code, but passing them does not certify specification correctness. We study a deployment-like monitoring problem: after code has p…
AMVICC: A Novel Benchmark for Cross-Modal Failure Mode Profiling for VLMs and IGMs
Aahana Basappa, Pranay Goel, Anusri Karra +3
We investigate visual reasoning limitations of both multimodal large language models (MLLMs) and image generation models (IGMs) by creating a novel benchmark to systematically comp…
MANATEE: Inference-Time Lightweight Diffusion Based Safety Defense for LLMs
Chun Yan Ryan Kan, Tommy Tran, Vedant Yadav +4
Defending LLMs against adversarial jailbreak attacks remains an open challenge. Existing defenses rely on binary classifiers that fail when adversarial input falls outside the lear…
MiSCHiEF: A Benchmark in Minimal-Pairs of Safety and Culture for Holistic Evaluation of Fine-Grained Image-Caption Alignment
Sagarika Banerjee, Tangatar Madi, Advait Swaminathan +4
Fine-grained image-caption alignment is crucial for vision-language models (VLMs), especially in socially critical contexts such as identifying real-world risk scenarios or disting…
Visualizing and Benchmarking LLM Factual Hallucination Tendencies via Internal State Analysis and Clustering
Nathan Mao, Varun Kaushik, Shreya Shivkumar +3
Large Language Models (LLMs) often hallucinate, generating nonsensical or false information that can be especially harmful in sensitive fields such as medicine or law. To study thi…
Zero-Shot Embedding Drift Detection: A Lightweight Defense Against Prompt Injections in LLMs
Anirudh Sekar, Mrinal Agarwal, Rachel Sharma +4
Prompt injection attacks have become an increasing vulnerability for LLM applications, where adversarial prompts exploit indirect input channels such as emails or user-generated co…