10 papers
Invisible Ink, Visible Lies: How Production Watermarking Causes LLMs to Hallucinate
Haocheng Ye, Aoting Hu, Xinwei Zhang +3
Text watermarking helps identify AI-generated content, but its effect on factual reliability remains underexplored. In this paper, we study watermarking hallucination: factual erro…
Black-Box Auditing of Epistemic Reliability in Multi-Agent Debate Distillation
Derui Wang, Zewei Shi, Rayne Holland +4
Debate distillation adapts weaker verifiers using multi-agent debate transcripts to improve their judgement in subsequent debates, but gains on monitored tasks do not establish rel…
FeatMark: Feature-level Watermark Protection against Mimicry Attacks with Diffusion Models
Haoyang Li, Ruoxi Sun, Qingqing Ye +4
Text-to-image diffusion models enable data-efficient "mimicry" attacks, wherein adversaries fine-tune the model on a handful of public photos to synthesize convincing forgeries of…
Beyond Her: Safety Dynamics in Role-play AI Companions
Zehang Deng, Zhaoyang Xie, Changzhou Han +8
The film 'Her' pictured a future of love between humans and AI. That future has quietly emerged in the form of Role-play AI Companions (RACs), where emotionally responsive interact…
Beyond Attack Success Rate: Examining Trigger Leakage in Vision-Language Agentic Systems
Jiamin Chang, Salil Kanhere, Piotr Koniusz +3
Vision-Language Agentic Systems (VLAS) connect visual perception to planning, tool use, and physical actions. This means backdoor-type triggers can propagate through both decision…
SoK: Unlearnability and Unlearning for Model Dememorization
Mengying Zhang, Derui Wang, Ruoxi Sun +3
Advanced model dememorization methods, including availability poisoning (unlearnability) and machine unlearning, are emerging as key safeguards against data misuse in machine learn…
LAPS: A Length-Aware-Prefill LLM Serving System
Jianshu She, Zonghang Li, Hongchao Du +7
LAPS identifies and disaggregates requests with different prompt lengths in LLM serving to reduce TTFT latency. While recent systems have decoupled the prefill and decode stages to…
Approximation Algorithm for Constrained -Center Clustering: A Local Search Approach
Chaoqi Jia, Longkun Guo, Kewen Liao +3
Clustering is a long-standing research problem and a fundamental tool in AI and data analysis. The traditional k-center problem, a fundamental theoretical challenge in clustering,…
Cross-Modal Unlearning via Influential Neuron Path Editing in Multimodal Large Language Models
Kunhao Li, Wenhao Li, Di Wu +4
Multimodal Large Language Models (MLLMs) extend foundation models to real-world applications by integrating inputs such as text and vision. However, their broad knowledge capacity…
Effects of Exponential Gaussian Distribution on (Double Sampling) Randomized Smoothing
Youwei Shu, Xi Xiao, Derui Wang +5
Randomized Smoothing (RS) is currently a scalable certified defense method providing robustness certification against adversarial examples. Although significant progress has been a…