Search Results for author:
Found 11 papers, 6 papers with code
Evaluating Decision Optimality of Autonomous Driving via Metamorphic Testing
In this paper, we focus on evaluating the decision-making quality of an ADS and propose the first method for detecting non-optimal decision scenarios (NoDSs), where the ADS does not compute optimal paths for AVs.
Making Them Ask and Answer: Jailbreaking Large Language Models in Few Queries via Disguise and Reconstruction
We evaluate DRA across various open-source and closed-source models, showcasing state-of-the-art jailbreak success rates and attack efficiency.
DataElixir: Purifying Poisoned Dataset to Mitigate Backdoor Attacks via Diffusion Models
Dataset sanitization is a widely adopted proactive defense against poisoning-based backdoor attacks, aimed at filtering out and removing poisoned samples from training datasets.
Good-looking but Lacking Faithfulness: Understanding Local Explanation Methods through Trend-based Testing
While enjoying the great achievements brought by deep learning (DL), people are also worried about the decision made by DL models, since the high degree of non-linearity of DL models makes the decision extremely difficult to understand.
ConFL: Constraint-guided Fuzzing for Machine Learning Framework
Guided by the constraints, ConFL is able to generate valid inputs that can pass the verification and explore deeper paths of kernel codes.
SSL-WM: A Black-Box Watermarking Approach for Encoders Pre-trained by Self-supervised Learning
Recent years have witnessed tremendous success in Self-Supervised Learning (SSL), which has been widely utilized to facilitate various downstream tasks in Computer Vision (CV) and Natural Language Processing (NLP) domains.
Learning Program Semantics with Code Representations: An Empirical Study
However, currently, a comprehensive and systematic study on evaluating different program representation techniques across diverse tasks is still missed.
GraphSearchNet: Enhancing GNNs via Capturing Global Dependencies for Semantic Code Search
Specifically, we propose to construct graphs for the source code and queries with bidirectional GGNN (BiGGNN) to capture the local structural information of the source code and queries.
DeepObliviate: A Powerful Charm for Erasing Data Residual Memory in Deep Neural Networks
Compared to the method of retraining from scratch, our approach can achieve 99. 0%, 95. 0%, 91. 9%, 96. 7%, 74. 1% accuracy rates and 66. 7$\times$, 75. 0$\times$, 33. 3$\times$, 29. 4$\times$, 13. 7$\times$ speedups on the MNIST, SVHN, CIFAR-10, Purchase, and ImageNet datasets, respectively.
Towards Security Threats of Deep Learning Systems: A Survey
In order to unveil the security weaknesses and aid in the development of a robust deep learning system, we undertake an investigation on attacks towards deep learning, and analyze these attacks to conclude some findings in multiple views.
Contextual Weisfeiler-Lehman Graph Kernel For Malware Detection
To address this, we develop the Contextual Weisfeiler-Lehman kernel (CWLK) which is capable of capturing both these types of information.
