153 citations · 224 across the 15 of their papers we have counts for
18 papers
Tripwire: Triggering Aligned Refusal via Statistically Certified Safety Neurons
Wei Zhao, Zhe Li, Peixin Zhang +1
Neuron- and path-level interventions offer the finest-grained route to defending large language models (LLMs) against jailbreak attacks, yet existing methods fall short of this pro…
Lossless Tensor Compression as Program Synthesis
Jieke Shi, Junda He, Wenjia Jiang +11
Model checkpoints are growing in both number and size, which makes archival, transfer, and deployment increasingly costly. General-purpose compressors can reduce storage requiremen…
Forecasting Side Effects of Activation Steering
Chong Yong Ong, Alson Wei Jie Sim, Peixin Zhang +1
Activation steering modifies a language model by adding a learned direction to its hidden activations, enabling targeted behavioral changes without retraining. While effective, ste…
DDOR: Delta Debugging for Explainable Overrefusal Testing and Repair
Qinyan Zhou, Peixin Zhang, Jun Sun +2
While safety alignment and guardrails help large language models (LLMs) avoid harmful outputs, they can also induce overrefusal, i.e., unwarranted rejection of benign queries that…
ClawGuard: A Runtime Security Framework for Tool-Augmented LLM Agents Against Indirect Prompt Injection
Wei Zhao, Zhe Li, Peixin Zhang +1
Tool-augmented Large Language Model (LLM) agents have demonstrated impressive capabilities in automating complex, multi-step real-world tasks, yet remain vulnerable to indirect pro…
Towards Provably Unlearnable Examples via Bayes Error Optimisation
Ruihan Zhang, Jun Sun, Ee-Peng Lim +1
The recent success of machine learning models, especially large-scale classifiers and language models, relies heavily on training with massive data. These data are often collected…
Rounding-Guided Backdoor Injection in Deep Learning Model Quantization
Xiangxiang Chen, Peixin Zhang, Jun Sun +2
Model quantization is a popular technique for deploying deep learning models on resource-constrained environments. However, it may also introduce previously overlooked security ris…
PRUNE: A Patching Based Repair Framework for Certifiable Unlearning of Neural Networks
Xuran Li, Jingyi Wang, Xiaohan Yuan +1
It is often desirable to remove (a.k.a. unlearn) a specific part of the training data from a trained neural network model. A typical application scenario is to protect the data hol…
RedTest: Towards Measuring Redundancy in Deep Neural Networks Effectively
Yao Lu, Peixin Zhang, Jingyi Wang +3
Deep learning has revolutionized computing in many real-world applications, arguably due to its remarkable performance and extreme convenience as an end-to-end solution. However, d…
LLMScan: Causal Scan for LLM Misbehavior Detection
Mengdi Zhang, Kai Kiat Goh, Peixin Zhang +3
Despite the success of Large Language Models (LLMs) across various fields, their potential to generate untruthful, biased and harmful responses poses significant risks, particularl…
Efficient and Universal Watermarking for LLM-Generated Code Detection
Boquan Li, Zirui Fu, Mengdi Zhang +3
Large language models (LLMs) have significantly enhanced the usability of AI-generated code, providing effective assistance to programmers. This advancement also raises ethical and…
Exploiting Machine Unlearning for Backdoor Attacks in Deep Learning System
Peixin Zhang, Jun Sun, Mingtian Tan +1
In recent years, the security issues of artificial intelligence have become increasingly prominent due to the rapid development of deep learning research and applications. Backdoor…
Towards Certified Probabilistic Robustness with High Accuracy
Ruihan Zhang, Peixin Zhang, Jun Sun
Adversarial examples pose a security threat to many critical systems built on neural networks (such as face recognition systems, and self-driving cars). While many methods have bee…
Influence of spin fluctuations on structural phase transitions of iron
Ning Wang, Thomas Hammerschmidt, Tilmann Hickel +2
The effect of spin fluctuations on the (bcc) - (fcc) - (bcc) structural phase transitions in iron is investigated with a tight-binding (TB) model. The orthogonal -va…
Automatic Fairness Testing of Neural Classifiers through Adversarial Sampling
Peixin Zhang, Jingyi Wang, Jun Sun +5
Although deep learning has demonstrated astonishing performance in many applications, there are still concerns about its dependability. One desirable property of deep learning appl…
There is Limited Correlation between Coverage and Robustness for Deep Neural Networks
Yizhen Dong, Peixin Zhang, Jingyi Wang +7
Deep neural networks (DNN) are increasingly applied in safety-critical systems, e.g., for face recognition, autonomous car control and malware detection. It is also shown that DNNs…
Adversarial Sample Detection for Deep Neural Network through Model Mutation Testing
Jingyi Wang, Guoliang Dong, Jun Sun +2
Deep neural networks (DNN) have been shown to be useful in a wide range of applications. However, they are also known to be vulnerable to adversarial samples. By transforming a nor…
Detecting Adversarial Samples for Deep Neural Networks through Mutation Testing
Jingyi Wang, Jun Sun, Peixin Zhang +1
Recently, it has been shown that deep neural networks (DNN) are subject to attacks through adversarial samples. Adversarial samples are often crafted through adversarial perturbati…