261 citations · 729 across the 22 of their papers we have counts for
23 papers
Rethinking Backdoor Attacks
Alaa Khaddaj, Guillaume Leclerc, Aleksandar Makelov +4
In a backdoor attack, an adversary inserts maliciously constructed backdoor examples into a training set to make the resulting model vulnerable to manipulation. Defending against s…
FFCV: Accelerating Training by Removing Data Bottlenecks
Guillaume Leclerc, Andrew Ilyas, Logan Engstrom +3
We present FFCV, a library for easy and fast machine learning model training. FFCV speeds up model training by eliminating (often subtle) data bottlenecks from the training process…
Raising the Cost of Malicious AI-Powered Image Editing
Hadi Salman, Alaa Khaddaj, Guillaume Leclerc +2
We present an approach to mitigating the risks of malicious image editing posed by large diffusion models. The key idea is to immunize images so as to make them resistant to manipu…
WaveNets: Wavelet Channel Attention Networks
Hadi Salman, Caleb Parks, Shi Yin Hong +1
Channel Attention reigns supreme as an effective technique in the field of computer vision. However, the proposed channel attention by SENet suffers from information loss in featur…
A Data-Based Perspective on Transfer Learning
Saachi Jain, Hadi Salman, Alaa Khaddaj +3
It is commonly believed that in transfer learning including more pre-training data translates into better performance. However, recent evidence suggests that removing data from the…
When does Bias Transfer in Transfer Learning?
Hadi Salman, Saachi Jain, Andrew Ilyas +3
Using transfer learning to adapt a pre-trained "source model" to a downstream "target task" can dramatically increase performance with seemingly no downside. In this work, we demon…
Missingness Bias in Model Debugging
Saachi Jain, Hadi Salman, Eric Wong +4
Missingness, or the absence of features from an input, is a concept fundamental to many model debugging tools. However, in computer vision, pixels cannot simply be removed from an…
Certified Patch Robustness via Smoothed Vision Transformers
Hadi Salman, Saachi Jain, Eric Wong +1
Certified patch defenses can guarantee robustness of an image classifier to arbitrary changes within a bounded contiguous region. But, currently, this robustness comes at a cost of…
CausalCity: Complex Simulations with Agency for Causal Discovery and Reasoning
Daniel McDuff, Yale Song, Jiyoung Lee +7
The ability to perform causal and counterfactual reasoning are central properties of human intelligence. Decision-making systems that can perform these types of reasoning have the…
3DB: A Framework for Debugging Computer Vision Models
Guillaume Leclerc, Hadi Salman, Andrew Ilyas +9
We introduce 3DB: an extendable, unified framework for testing and debugging vision models using photorealistic simulation. We demonstrate, through a wide range of use cases, that…
Unadversarial Examples: Designing Objects for Robust Vision
Hadi Salman, Andrew Ilyas, Logan Engstrom +3
We study a class of realistic computer vision settings wherein one can influence the design of the objects being recognized. We develop a framework that leverages this capability t…
Do Adversarially Robust ImageNet Models Transfer Better?
Hadi Salman, Andrew Ilyas, Logan Engstrom +2
Transfer learning is a widely-used paradigm in deep learning, where models pre-trained on standard datasets can be efficiently adapted to downstream tasks. Typically, better pre-tr…
Improved Image Wasserstein Attacks and Defenses
Edward J. Hu, Adith Swaminathan, Hadi Salman +1
Robustness against image perturbations bounded by a ball have been well-studied in recent literature. Perturbations in the real-world, however, rarely exhibit the pixel in…
Denoised Smoothing: A Provable Defense for Pretrained Classifiers
Hadi Salman, Mingjie Sun, Greg Yang +2
We present a method for provably defending any pretrained image classifier against adversarial attacks. This method, for instance, allows public vision API providers and u…
Randomized Smoothing of All Shapes and Sizes
Greg Yang, Tony Duan, J. Edward Hu +3
Randomized smoothing is the current state-of-the-art defense with provable robustness against adversarial attacks. Many works have devised new randomized smoothing schemes…
A Fine-Grained Spectral Perspective on Neural Networks
Greg Yang, Hadi Salman
Are neural networks biased toward simple functions? Does depth always help learn more complex features? Is training the last layer of a network as good as training all layers? How…
Provably Robust Deep Learning via Adversarially Trained Smoothed Classifiers
Hadi Salman, Greg Yang, Jerry Li +4
Recent works have shown the effectiveness of randomized smoothing as a scalable technique for building neural network-based classifiers that are provably robust to -norm ad…
A Convex Relaxation Barrier to Tight Robustness Verification of Neural Networks
Hadi Salman, Greg Yang, Huan Zhang +2
Verification of neural networks enables us to gauge their robustness against adversarial attacks. Verification algorithms fall into two categories: exact verifiers that run in expo…
Deep Diffeomorphic Normalizing Flows
Hadi Salman, Payman Yadollahpour, Tom Fletcher +1
The Normalizing Flow (NF) models a general probability density by estimating an invertible transformation applied on samples drawn from a known distribution. We introduce a new typ…
Learning to Sequence Robot Behaviors for Visual Navigation
Hadi Salman, Puneet Singhal, Tanmay Shankar +6
Recent literature in the robotics community has focused on learning robot behaviors that abstract out lower-level details of robot control. To fully leverage the efficacy of such b…
A surgical system for automatic registration, stiffness mapping and dynamic image overlay
Nicolas Zevallos, Rangaprasad Arun Srivatsan, Hadi Salman +6
In this paper we develop a surgical system using the da Vinci research kit (dVRK) that is capable of autonomously searching for tumors and dynamically displaying the tumor location…
Trajectory-Optimized Sensing for Active Search of Tissue Abnormalities in Robotic Surgery
Hadi Salman, Elif Ayvali, Rangaprasad Arun Srivatsan +6
In this work, we develop an approach for guiding robots to automatically localize and find the shapes of tumors and other stiff inclusions present in the anatomy. Our approach uses…
Ergodic Coverage In Constrained Environments Using Stochastic Trajectory Optimization
Elif Ayvali, Hadi Salman, Howie Choset
In search and surveillance applications in robotics, it is intuitive to spatially distribute robot trajectories with respect to the probability of locating targets in the domain. E…