281 citations · 694 across the 15 of their papers we have counts for
15 papers
Greener yet Powerful: Taming Large Code Generation Models with Quantization
Xiaokai Wei, Sujan Gonugondla, Wasi Ahmad +13
ML-powered code generation aims to assist developers to write code in a more productive manner, by intelligently generating code blocks based on natural language prompts. Recently,…
Are Diffusion Models Vulnerable to Membership Inference Attacks?
Jinhao Duan, Fei Kong, Shiqi Wang +2
Diffusion-based generative models have shown great potential for image synthesis, but there is a lack of research on the security and privacy risks they may pose. In this paper, we…
ReCode: Robustness Evaluation of Code Generation Models
Shiqi Wang, Zheng Li, Haifeng Qian +11
Code generation models have achieved impressive performance. However, they tend to be brittle as slight edits to a prompt could lead to very different generations; these robustness…
Multi-lingual Evaluation of Code Generation Models
Ben Athiwaratkun, Sanjay Krishna Gouda, Zijian Wang +22
We present new benchmarks on evaluation code generation models: MBXP and Multilingual HumanEval, and MathQA-X. These datasets cover over 10 programming languages and are generated…
General Cutting Planes for Bound-Propagation-Based Neural Network Verification
Huan Zhang, Shiqi Wang, Kaidi Xu +5
Bound propagation methods, when combined with branch and bound, are among the most effective methods to formally verify properties of deep neural networks such as correctness, robu…
Learning Security Classifiers with Verified Global Robustness Properties
Yizheng Chen, Shiqi Wang, Yue Qin +3
Many recent works have proposed methods to train classifiers with local robustness properties, which can provably eliminate classes of evasion attacks for most inputs, but not all…
Adaptive Verifiable Training Using Pairwise Class Similarity
Shiqi Wang, Kevin Eykholt, Taesung Lee +2
Verifiable training has shown success in creating neural networks that are provably robust to a given amount of noise. However, despite only enforcing a single robustness criterion…
Fast and Complete: Enabling Complete Neural Network Verification with Rapid and Massively Parallel Incomplete Verifiers
Kaidi Xu, Huan Zhang, Shiqi Wang +4
Formal verification of neural networks (NNs) is a challenging and important problem. Existing efficient complete solvers typically require the branch-and-bound (BaB) process, which…
Towards Understanding Fast Adversarial Training
Bai Li, Shiqi Wang, Suman Jana +1
Current neural-network-based classifiers are susceptible to adversarial examples. The most empirically successful approach to defending against such adversarial examples is adversa…
Towards Practical Lottery Ticket Hypothesis for Adversarial Training
Bai Li, Shiqi Wang, Yunhan Jia +4
Recent research has proposed the lottery ticket hypothesis, suggesting that for a deep neural network, there exist trainable sub-networks performing equally or better than the orig…
Towards Compact and Robust Deep Neural Networks
Vikash Sehwag, Shiqi Wang, Prateek Mittal +1
Deep neural networks have achieved impressive performance in many applications but their large number of parameters lead to significant computational and storage overheads. Several…
Enhancing Gradient-based Attacks with Symbolic Intervals
Shiqi Wang, Yizheng Chen, Ahmed Abdou +1
Recent breakthroughs in defenses against adversarial examples, like adversarial training, make the neural networks robust against various classes of attackers (e.g., first-order gr…
On Training Robust PDF Malware Classifiers
Yizheng Chen, Shiqi Wang, Dongdong She +1
Although state-of-the-art PDF malware classifiers can be trained with almost perfect test accuracy (99%) and extremely low false positive rate (under 0.1%), it has been shown that…
Efficient Formal Safety Analysis of Neural Networks
Shiqi Wang, Kexin Pei, Justin Whitehouse +2
Neural networks are increasingly deployed in real-world safety-critical domains such as autonomous driving, aircraft collision avoidance, and malware detection. However, these netw…
Formal Security Analysis of Neural Networks using Symbolic Intervals
Shiqi Wang, Kexin Pei, Justin Whitehouse +2
Due to the increasing deployment of Deep Neural Networks (DNNs) in real-world security-critical domains including autonomous vehicles and collision avoidance systems, formally chec…