5 citations · 5 across the 10 of their papers we have counts for
10 papers
ProbGuard: Calibrated Safety Risk Estimation from LLM Output Distributions
Xinzhe Huang, Biwu Yao, Kedong Xiu +4
Recent research on Large Language Model (LLM) safety has widely adopted guardrails to identify unsafe LLM outputs. Existing guardrails typically formulate safety assessment as a de…
AgentSnare: Learning to Delay, Divert, and Defuse Autonomous Penetration Agents
Ruoyu Wang, Heng Zhao, Renjie Wu +4
Large language model (LLM) agents automate penetration testing through an observation-action loop, selecting actions based on observations returned by tools. This dependence allows…
Confusion-Geometry Rebalancing for Long-Tailed Adversarial Training
Mengnan Zhao, Geyong Min, Lihe Zhang +2
Adversarial training under long tailed distributions suffers from a dual imbalance: the class imbalance skews the training objective toward head classes, and the adversarial inner…
CoreUnlearn: Rethinking Concept Unlearning through Disentangled Component-Level Erasure in Text-guided Diffusion Models
Mengnan Zhao, Lihe Zhang, Baocai Yin
Text guided diffusion models have revolutionized image synthesis but also raise ethical concerns, such as privacy violation and harmful content generation. To mitigate these issues…
Unveiling the Backdoor Mechanism Hidden Behind Catastrophic Overfitting in Fast Adversarial Training
Mengnan Zhao, Lihe Zhang, Tianhang Zheng +2
Fast Adversarial Training (FAT) has attracted significant attention due to its efficiency in enhancing neural network robustness against adversarial attacks. However, FAT is prone…
Mitigating Error Amplification in Fast Adversarial Training
Mengnan Zhao, Lihe Zhang, Bo Wang +3
Fast Adversarial Training (FAT) has proven effective in enhancing model robustness by encouraging networks to learn perturbation-invariant representations. However, FAT often suffe…
AdvAnchor: Enhancing Diffusion Model Unlearning with Adversarial Anchors
Mengnan Zhao, Lihe Zhang, Xingyi Yang +2
Security concerns surrounding text-to-image diffusion models have driven researchers to unlearn inappropriate concepts through fine-tuning. Recent fine-tuning methods typically ali…
Adversarial Training: A Survey
Mengnan Zhao, Lihe Zhang, Jingwen Ye +3
Adversarial training (AT) refers to integrating adversarial examples -- inputs altered with imperceptible perturbations that can significantly impact model predictions -- into the…
Catastrophic Overfitting: A Potential Blessing in Disguise
Mengnan Zhao, Lihe Zhang, Yuqiu Kong +1
Fast Adversarial Training (FAT) has gained increasing attention within the research community owing to its efficacy in improving adversarial robustness. Particularly noteworthy is…
Separable Multi-Concept Erasure from Diffusion Models
Mengnan Zhao, Lihe Zhang, Tianhang Zheng +2
Large-scale diffusion models, known for their impressive image generation capabilities, have raised concerns among researchers regarding social impacts, such as the imitation of co…