LLM Misalignment via Adversarial RLHF Platforms.

OverThink: Slowdown Attacks on Reasoning LLMs.

Riddle Me This! Stealthy Membership Inference for Retrieval-Augmented Generation.

Synthetic Data Can Mislead Evaluations: Membership Inference as Machine Text Detection.

Injecting Bias in Text-To-Image Models via Composite-Trigger Backdoors.

Iteratively Prompting Multimodal LLMs to Reproduce Natural and AI-Generated Images.

Understanding (Un)Intended Memorization in Text-to-Image Generative Models.

Memory Triggers: Unveiling Memorization in Text-To-Image Generative Models through Word-Level Duplication.

On the Risks of Stealing the Decoding Algorithms of Language Models.