2 citations · 2 across the 11 of their papers we have counts for
12 papers
Crossing the Margin Cliff: Toward Relearn-Robust LLM Unlearning via Margin Calibration
Xiangyu Yin, Jiaxu Liu, Zhen Chen +1
Large language model unlearning is consistently fragile under relearn attacks. On TOFU, fine-tuning on twenty forget examples substantially recovers held-out forget-set ROUGE for e…
Fragile by Design: On the Limits of Adversarial Defenses in Personalized Generation
Zhen Chen, Yi Zhang, Xiangyu Yin +4
Personalized AI applications such as DreamBooth enable the generation of customized content from user images, but also raise significant privacy concerns, particularly the risk of…
Cumulative Consensus Score: Label-Free and Model-Agnostic Evaluation of Object Detectors in Deployment
Avinaash Manoharan, Xiangyu Yin, Domenik Helm +1
Evaluating object detection models in deployment is challenging because ground-truth annotations are rarely available. We introduce the Cumulative Consensus Score (CCS), a label-fr…
TAIJI: Textual Anchoring for Immunizing Jailbreak Images in Vision Language Models
Xiangyu Yin, Yi Qi, Jinwei Hu +5
Vision Language Models (VLMs) have demonstrated impressive inference capabilities, but remain vulnerable to jailbreak attacks that can induce harmful or unethical responses. Existi…
CeTAD: Towards Certified Toxicity-Aware Distance in Vision Language Models
Xiangyu Yin, Jiaxu Liu, Zhen Chen +4
Recent advances in large vision-language models (VLMs) have demonstrated remarkable success across a wide range of visual understanding tasks. However, the robustness of these mode…
FALCON: Fine-grained Activation Manipulation by Contrastive Orthogonal Unalignment for Large Language Model
Jinwei Hu, Zhenglin Huang, Xiangyu Yin +4
Large language models have been widely applied, but can inadvertently encode sensitive or harmful information, raising significant safety concerns. Machine unlearning has emerged t…
A Black-Box Evaluation Framework for Semantic Robustness in Bird's Eye View Detection
Fu Wang, Yanghao Zhang, Xiangyu Yin +4
Camera-based Bird's Eye View (BEV) perception models receive increasing attention for their crucial role in autonomous driving, a domain where concerns about the robustness and rel…
Robust RL with LLM-Driven Data Synthesis and Policy Adaptation for Autonomous Driving
Sihao Wu, Jiaxu Liu, Xiangyu Yin +5
The integration of Large Language Models (LLMs) into autonomous driving systems demonstrates strong common sense and reasoning abilities, effectively addressing the pitfalls of pur…
Tiny Refinements Elicit Resilience: Toward Efficient Prefix-Model Against LLM Red-Teaming
Jiaxu Liu, Xiangyu Yin, Sihao Wu +4
With the proliferation of red-teaming strategies for Large Language Models (LLMs), the deficiency in the literature about improving the safety and robustness of LLM defense strateg…
Continuous Geometry-Aware Graph Diffusion via Hyperbolic Neural PDE
Jiaxu Liu, Xinping Yi, Sihao Wu +4
While Hyperbolic Graph Neural Network (HGNN) has recently emerged as a powerful tool dealing with hierarchical graph data, the limitations of scalability and efficiency hinder itse…
Boosting Adversarial Training via Fisher-Rao Norm-based Regularization
Xiangyu Yin, Wenjie Ruan
Adversarial training is extensively utilized to improve the adversarial robustness of deep neural networks. Yet, mitigating the degradation of standard generalization performance i…
ReRoGCRL: Representation-based Robustness in Goal-Conditioned Reinforcement Learning
Xiangyu Yin, Sihao Wu, Jiaxu Liu +4
While Goal-Conditioned Reinforcement Learning (GCRL) has gained attention, its algorithmic robustness against adversarial perturbations remains unexplored. The attacks and robust r…