5 papers
PersonaAct: Simulating Short-Video Users with Personalized Agents for Counterfactual Filter Bubble Auditing
Shilong Zhao, Qinggang Yang, Zhiyi Yin +4
Short-video platforms rely on personalized recommendation, raising concerns about filter bubbles that narrow content exposure. Auditing such phenomena at scale is challenging becau…
BSFA: Leveraging the Subspace Dichotomy to Accelerate Neural Network Training
Wenjie Zhou, Bohan Wang, Wei Chen +1
Recent studies \citep{gur2018gradient,song2024does, wen2024understanding} highlight a fundamental dichotomy in deep learning optimization: Although parameter updates along the top…
Speculative Safety-Aware Decoding
Xuekang Wang, Shengyu Zhu, Xueqi Cheng
Despite extensive efforts to align Large Language Models (LLMs) with human values and safety rules, jailbreak attacks that exploit certain vulnerabilities continuously emerge, high…
Rethinking Machine Unlearning in Image Generation Models
Renyang Liu, Wenjie Feng, Tianwei Zhang +3
With the surge and widespread application of image generation models, data privacy and content safety have become major concerns and attracted great attention from users, service p…
MISLEADER: Defending against Model Extraction with Ensembles of Distilled Models
Xueqi Cheng, Minxing Zheng, Shixiang Zhu +1
Model extraction attacks aim to replicate the functionality of a black-box model through query access, threatening the intellectual property (IP) of machine-learning-as-a-service (…