12 papers
Reactivating Alignment: Defending LLMs from Jailbreaks via Intention-Aware Input-Output Matching
Luoyu Chen, Weiqi Wang, Chenhan Zhang +2
Large language models (LLMs) remain vulnerable to jailbreak attacks that conceal harmful intent within complex adversarial prompts. Existing defenses primarily rely on input pertur…
Target-free Latent Safety Alignment
Luoyu Chen, Weiqi Wang, Chenhan Zhang +3
Large language models (LLMs) remain highly vulnerable to jailbreak attacks that induce harmful behaviors and circumvent safety alignment. To defend against such attacks, adversaria…
Steering Beyond the Support: Adversarial Training on Unsupervised Jailbroken Activation Simulation
Luoyu Chen, Weiqi Wang, Zhiyi Tian +5
Jailbreak prompts can trigger harmful completions on aligned LLMs, In accordance, safety steering has been proposed: test-time activation interventions that steer jailbreak activat…
Ellipsoid Control: A White-list Jailbreak Defense via Benign Latent Modeling
Luoyu Chen, Weiqi Wang, Zhiyi Tian +3
Representation engineering (RepE) defenses have shown strong robustness against jailbreak attacks on large language models (LLMs). However, these methods fundamentally rely on blac…
Approximate Machine Unlearning through Manifold Representation Forgetting Guided by Self Mode Connectivity
Weiqi Wang, Zhiyi Tian, Chenhan Zhang +2
Machine unlearning is a fundamental mechanism that enforces the right to be forgotten. Existing unlearning studies that rely on label manipulation or task-gradient reversal often d…
GeoIB: Geometry-Aware Information Bottleneck via Statistical-Manifold Compression
Weiqi Wang, Zhiyi Tian, Chenhan Zhang +1
Information Bottleneck (IB) is widely used, but in deep learning, it is usually implemented through tractable surrogates, such as variational bounds or neural mutual information (M…
EVE: Efficient Verification of Data Erasure through Customized Perturbation in Approximate Unlearning
Weiqi Wang, Zhiyi Tian, Chenhan Zhang +2
Verifying whether the machine unlearning process has been properly executed is critical but remains underexplored. Some existing approaches propose unlearning verification methods…
BlindU: Blind Machine Unlearning without Revealing Erasing Data
Weiqi Wang, Zhiyi Tian, Chenhan Zhang +1
Machine unlearning enables data holders to remove the contribution of their specified samples from trained models to protect their privacy. However, it is paradoxical that most unl…
SMS: Self-supervised Model Seeding for Verification of Machine Unlearning
Weiqi Wang, Chenhan Zhang, Zhiyi Tian +1
Many machine unlearning methods have been proposed recently to uphold users' right to be forgotten. However, offering users verification of their data removal post-unlearning is an…
CRFU: Compressive Representation Forgetting Against Privacy Leakage on Machine Unlearning
Weiqi Wang, Chenhan Zhang, Zhiyi Tian +2
Machine unlearning allows data owners to erase the impact of their specified data from trained models. Unfortunately, recent studies have shown that adversaries can recover the era…
SCU: An Efficient Machine Unlearning Scheme for Deep Learning Enabled Semantic Communications
Weiqi Wang, Zhiyi Tian, Chenhan Zhang +1
Deep learning (DL) enabled semantic communications leverage DL to train encoders and decoders (codecs) to extract and recover semantic information. However, most semantic training…
Can Self Supervision Rejuvenate Similarity-Based Link Prediction?
Chenhan Zhang, Weiqi Wang, Zhiyi Tian +4
Although recent advancements in end-to-end learning-based link prediction (LP) methods have shown remarkable capabilities, the significance of traditional similarity-based LP metho…