34 citations · 93 across the 10 of their papers we have counts for
12 papers
Stable Diffusion Models are Secretly Good at Visual In-Context Learning
Trevine Oorloff, Vishwanath Sindagi, Wele Gedara Chaminda Bandara +4
Large language models (LLM) in natural language processing (NLP) have demonstrated great potential for in-context learning (ICL) -- the ability to leverage a few sets of example pr…
What do Vision Transformers Learn? A Visual Exploration
Amin Ghiasi, Hamid Kazemi, Eitan Borgnia +5
Vision transformers (ViTs) are quickly becoming the de-facto architecture for computer vision, yet we understand very little about why they work and what they learn. While existing…
Improving Robustness with Adaptive Weight Decay
Amin Ghiasi, Ali Shafahi, Reza Ardekani
We propose adaptive weight decay, which automatically tunes the hyper-parameter for weight decay during each training iteration. For classification problems, we propose changing th…
Plug-In Inversion: Model-Agnostic Inversion for Vision with Data Augmentations
Amin Ghiasi, Hamid Kazemi, Steven Reich +3
Existing techniques for model inversion typically rely on hard-to-tune regularizers, such as total variation or feature regularization, which must be individually calibrated for ea…
DP-InstaHide: Provably Defusing Poisoning and Backdoor Attacks with Differentially Private Data Augmentations
Eitan Borgnia, Jonas Geiping, Valeriia Cherepanova +6
Data poisoning and backdoor attacks manipulate training data to induce security breaches in a victim model. These attacks can be provably deflected using differentially private (DP…
The Uncanny Similarity of Recurrence and Depth
Avi Schwarzschild, Arjun Gupta, Amin Ghiasi +2
It is widely believed that deep neural networks contain layer specialization, wherein neural networks extract hierarchical features representing edges and patterns in shallow layer…
Strong Data Augmentation Sanitizes Poisoning and Backdoor Attacks Without an Accuracy Tradeoff
Eitan Borgnia, Valeriia Cherepanova, Liam Fowl +5
Data poisoning and backdoor attacks manipulate victim models by maliciously modifying training data. In light of this growing threat, a recent survey of industry professionals reve…
Towards Accurate Quantization and Pruning via Data-free Knowledge Transfer
Chen Zhu, Zheng Xu, Ali Shafahi +3
When large scale training data is available, one can obtain compact and accurate networks to be deployed in resource-constrained environments effectively through quantization and p…
Breaking certified defenses: Semantic adversarial examples with spoofed robustness certificates
Amin Ghiasi, Ali Shafahi, Tom Goldstein
To deflect adversarial attacks, a range of "certified" classifiers have been proposed. In addition to labeling an image, certified classifiers produce (when possible) a certificate…
Label Smoothing and Logit Squeezing: A Replacement for Adversarial Training?
Ali Shafahi, Amin Ghiasi, Furong Huang +1
Adversarial training is one of the strongest defenses against adversarial attacks, but it requires adversarial examples to be generated for every mini-batch during optimization. Th…
Adversarially robust transfer learning
Ali Shafahi, Parsa Saadatpanah, Chen Zhu +4
Transfer learning, in which a network is trained on one task and re-purposed on another, is often used to produce neural network classifiers when data is scarce or full-scale train…
Adversarial Training for Free!
Ali Shafahi, Mahyar Najibi, Amin Ghiasi +6
Adversarial training, in which a network is trained on adversarial examples, is one of the few defenses against adversarial attacks that withstands strong attacks. Unfortunately, t…