114 citations · 417 across the 32 of their papers we have counts for
33 papers
Does More Inference-Time Compute Really Help Robustness?
Tong Wu, Chong Xiang, Jiachen T. Wang +4
Recently, Zaremba et al. demonstrated that increasing inference-time computation improves robustness in large proprietary reasoning LLMs. In this paper, we first show that smaller-…
CO-SPY: Combining Semantic and Pixel Features to Detect Synthetic Images by AI
Siyuan Cheng, Lingjuan Lyu, Zhenting Wang +2
With the rapid advancement of generative AI, it is now possible to synthesize high-quality images in a few seconds. Despite the power of these technologies, they raise significant…
Adapting to Evolving Adversaries with Regularized Continual Robust Training
Sihui Dai, Christian Cianfarani, Arjun Bhagoji +2
Robust training methods typically defend against specific attack types, such as Lp attacks with fixed budgets, and rarely account for the fact that defenders may encounter new atta…
Self-Comparison for Dataset-Level Membership Inference in Large (Vision-)Language Models
Jie Ren, Kangrui Chen, Chen Chen +4
Large Language Models (LLMs) and Vision-Language Models (VLMs) have made significant advancements in a wide range of natural language processing and vision-language tasks. Access t…
Activity Recognition on Avatar-Anonymized Datasets with Masked Differential Privacy
David Schneider, Sina Sajadmanesh, Vikash Sehwag +4
Privacy-preserving computer vision is an important emerging problem in machine learning and artificial intelligence. Prevalent methods tackling this problem use differential privac…
Stretching Each Dollar: Diffusion Training from Scratch on a Micro-Budget
Vikash Sehwag, Xianghao Kong, Jingtao Li +2
As scaling laws in generative AI push performance, they also simultaneously concentrate the development of these models among actors with large computational resources. With a focu…
Evaluating and Mitigating IP Infringement in Visual Generative AI
Zhenting Wang, Chen Chen, Vikash Sehwag +2
The popularity of visual generative AI models like DALL-E 3, Stable Diffusion XL, Stable Video Diffusion, and Sora has been increasing. Through extensive evaluation, we discovered…
AI Risk Management Should Incorporate Both Safety and Security
Xiangyu Qi, Yangsibo Huang, Yi Zeng +22
The exposure of security vulnerabilities in safety-aligned language models, e.g., susceptibility to adversarial attacks, has shed light on the intricate interplay between AI safety…
How to Trace Latent Generative Model Generated Images without Artificial Watermark?
Zhenting Wang, Vikash Sehwag, Chen Chen +3
Latent generative models (e.g., Stable Diffusion) have become more and more popular, but concerns have arisen regarding potential misuse related to images generated by these models…
JailbreakBench: An Open Robustness Benchmark for Jailbreaking Large Language Models
Patrick Chao, Edoardo Debenedetti, Alexander Robey +9
Jailbreak attacks cause large language models (LLMs) to generate harmful, unethical, or otherwise objectionable content. Evaluating these attacks presents a number of challenges, w…
Finding needles in a haystack: A Black-Box Approach to Invisible Watermark Detection
Minzhou Pan, Zhenting Wang, Xin Dong +3
In this paper, we propose WaterMark Detection (WMD), the first invisible watermark detection method under a black-box and annotation-free setting. WMD is capable of detecting arbit…
Scaling Compute Is Not All You Need for Adversarial Robustness
Edoardo Debenedetti, Zishen Wan, Maksym Andriushchenko +3
The last six years have witnessed significant progress in adversarially robust deep learning. As evidenced by the CIFAR-10 dataset category in RobustBench benchmark, the accuracy u…
Differentially Private Image Classification by Learning Priors from Random Processes
Xinyu Tang, Ashwinee Panda, Vikash Sehwag +1
In privacy-preserving machine learning, differentially private stochastic gradient descent (DP-SGD) performs worse than SGD due to per-sample gradient clipping and noise addition.…
Uncovering Adversarial Risks of Test-Time Adaptation
Tong Wu, Feiran Jia, Xiangyu Qi +4
Recently, test-time adaptation (TTA) has been proposed as a promising solution for addressing distribution shifts. It allows a base model to adapt to an unforeseen distribution dur…
MultiRobustBench: Benchmarking Robustness Against Multiple Attacks
Sihui Dai, Saeed Mahloujifar, Chong Xiang +3
The bulk of existing research in defending against adversarial examples focuses on defending against a single (typically bounded Lp-norm) attack, but for a practical setting, machi…
Extracting Training Data from Diffusion Models
Nicholas Carlini, Jamie Hayes, Milad Nasr +6
Image diffusion models such as DALL-E 2, Imagen, and Stable Diffusion have attracted significant attention due to their ability to generate high-quality synthetic images. In this w…
A New Linear Scaling Rule for Private Adaptive Hyperparameter Optimization
Ashwinee Panda, Xinyu Tang, Saeed Mahloujifar +2
An open problem in differentially private deep learning is hyperparameter optimization (HPO). DP-SGD introduces new hyperparameters and complicates existing ones, forcing researche…
A Light Recipe to Train Robust Vision Transformers
Edoardo Debenedetti, Vikash Sehwag, Prateek Mittal
In this paper, we ask whether Vision Transformers (ViTs) can serve as an underlying architecture for improving the adversarial robustness of machine learning models against evasion…
Just Rotate it: Deploying Backdoor Attacks via Rotation Transformation
Tong Wu, Tianhao Wang, Vikash Sehwag +2
Recent works have demonstrated that deep learning models are vulnerable to backdoor poisoning attacks, where these attacks instill spurious correlations to external trigger pattern…
Understanding Robust Learning through the Lens of Representation Similarities
Christian Cianfarani, Arjun Nitin Bhagoji, Vikash Sehwag +3
Representation learning, i.e. the generation of representations useful for downstream applications, is a task of fundamental importance that underlies much of the success of deep n…
Generating High Fidelity Data from Low-density Regions using Diffusion Models
Vikash Sehwag, Caner Hazirbas, Albert Gordo +2
Our work focuses on addressing sample deficiency from low-density regions of data manifold in common image datasets. We leverage diffusion process based generative models to synthe…
Robust Learning Meets Generative Models: Can Proxy Distributions Improve Adversarial Robustness?
Vikash Sehwag, Saeed Mahloujifar, Tinashe Handina +4
While additional training data improves the robustness of deep neural networks against adversarial examples, it presents the challenge of curating a large number of specific real-w…
Lower Bounds on Cross-Entropy Loss in the Presence of Test-time Adversaries
Arjun Nitin Bhagoji, Daniel Cullina, Vikash Sehwag +1
Understanding the fundamental limits of robust supervised learning has emerged as a problem of immense interest, from both practical and theoretical standpoints. In particular, it…
SSD: A Unified Framework for Self-Supervised Outlier Detection
Vikash Sehwag, Mung Chiang, Prateek Mittal
We ask the following question: what training information is required to design an effective outlier/out-of-distribution (OOD) detector, i.e., detecting samples that lie far away fr…