Search Results for author: Sicheng Zhu

Found 7 papers, 5 papers with code

Benchmarking the Robustness of Image Watermarks

1 code implementation16 Jan 2024 Bang An, Mucong Ding, Tahseen Rabbani, Aakriti Agrawal, Yuancheng Xu, ChengHao Deng, Sicheng Zhu, Abdirisak Mohamed, Yuxin Wen, Tom Goldstein, Furong Huang

We present WAVES (Watermark Analysis Via Enhanced Stress-testing), a novel benchmark for assessing watermark robustness, overcoming the limitations of current evaluation methods. WAVES integrates detection and identification tasks, and establishes a standardized evaluation protocol comprised of a diverse range of stress tests.

Benchmarking

AutoDAN: Interpretable Gradient-Based Adversarial Attacks on Large Language Models

1 code implementation23 Oct 2023 Sicheng Zhu, Ruiyi Zhang, Bang An, Gang Wu, Joe Barrow, Zichao Wang, Furong Huang, Ani Nenkova, Tong Sun

Safety alignment of Large Language Models (LLMs) can be compromised with manual jailbreak attacks and (automatic) adversarial attacks.

Adversarial Attack Blocking

PerceptionCLIP: Visual Classification by Inferring and Conditioning on Contexts

1 code implementation2 Aug 2023 Bang An, Sicheng Zhu, Michael-Andrei Panaitescu-Liess, Chaithanya Kumar Mummadi, Furong Huang

Inspired by it, we observe that providing CLIP with contextual attributes improves zero-shot image classification and mitigates reliance on spurious features.

Classification Image Classification +4

On the Possibilities of AI-Generated Text Detection

no code implementations10 Apr 2023 Souradip Chakraborty, Amrit Singh Bedi, Sicheng Zhu, Bang An, Dinesh Manocha, Furong Huang

Our work addresses the critical issue of distinguishing text generated by Large Language Models (LLMs) from human-produced text, a task essential for numerous applications.

Text Detection

Understanding the Generalization Benefit of Model Invariance from a Data Perspective

1 code implementation NeurIPS 2021 Sicheng Zhu, Bang An, Furong Huang

Based on this notion, we refine the generalization bound for invariant models and characterize the suitability of a set of data transformations by the sample covering number induced by transformations, i. e., the smallest size of its induced sample covers.

Generalization Bounds

Learning Adversarially Robust Representations via Worst-Case Mutual Information Maximization

1 code implementation ICML 2020 Sicheng Zhu, Xiao Zhang, David Evans

We develop a notion of representation vulnerability that captures the maximum change of mutual information between the input and output distributions, under the worst-case input perturbation.

Adversarial Robustness

Guess First to Enable Better Compression and Adversarial Robustness

no code implementations10 Jan 2020 Sicheng Zhu, Bang An, Shiyu Niu

Machine learning models are generally vulnerable to adversarial examples, which is in contrast to the robustness of humans.

Adversarial Robustness

Cannot find the paper you are looking for? You can Submit a new open access paper.