Ali Shafahi — accepted AI-conference papers

2025

Stable Diffusion Models are Secretly Good at Visual In-Context Learning

Trevine Oorloff, Vishwanath Sindagi, Wele Gedara Chaminda Bandara, Ali Shafahi, Amin Ghiasi, Charan Prakash +1

ICCV 2025poster

Large language models (LLM) in natural language processing (NLP) have demonstrated great potential for in-context learning (ICL) -- the ability to leverage a few set of example prompts to adapt to various tasks without having to explicitly update model weights. ICL has recently been explored for the…

Cited by 0 Source ↗PDF ↗Scholar ↗

2023

Improving Robustness with Adaptive Weight Decay

Amin Ghiasi, Ali Shafahi, Reza Ardekani

NeurIPS 2023poster

We propose adaptive weight decay, which automatically tunes the hyper-parameter for weight decay during each training iteration. For classification problems, we propose changing the value of the weight decay hyper-parameter on the fly based on the strength of updates from the classification loss (i.…

Cited by 8 Source ↗PDF ↗Scholar ↗

2020

Adversarial Attacks on Copyright Detection Systems

Parsa Saadatpanah, Ali Shafahi, Tom Goldstein

ICML 2020poster

It is well-known that many machine learning models are susceptible to adversarial attacks, in which an attacker evades a classifier by making small perturbations to inputs. This paper discusses how industrial copyright detection tools, which serve a central role on the web, are susceptible to advers…

Cited by 51 Source ↗PDF ↗Scholar ↗

2020

Adversarially robust transfer learning

Ali Shafahi, Parsa Saadatpanah, Chen Zhu, Amin Ghiasi, Christoph Studer, David Jacobs +1

ICLR 2020poster

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 training is too costly. When the goal is to produce a model that is not only accurate but also adversarially robust, data sc…

Cited by 157 Source ↗code ↗Scholar ↗

2020

BREAKING CERTIFIED DEFENSES: SEMANTIC ADVERSARIAL EXAMPLES WITH SPOOFED ROBUSTNESS CERTIFICATES

Amin Ghiasi, Ali Shafahi, Tom Goldstein

ICLR 2020poster

Defenses against adversarial attacks can be classified into certified and non-certified. Certifiable defenses make networks robust within a certain $\ell_p$-bounded radius, so that it is impossible for the adversary to make adversarial examples in the certificate bound. We present an attack that mai…

Cited by 84 Source ↗code ↗Scholar ↗

2020

Witchcraft: Efficient PGD Attacks with Random Step Size

Ping-Yeh Chiang, Jonas Geiping, Micah Goldblum, Tom Goldstein, Renkun Ni, Steven Reich +1

ICASSP 2020accepted

State-of-the-art adversarial attacks on neural networks use expensive iterative methods and numerous random restarts from different initial points. Iterative FGSM-based methods without restarts trade off performance for computational efficiency because they do not adequately explore the image space…

Cited by 0 Source ↗Scholar ↗

2019

Adversarial training for free!

Ali Shafahi, Mahyar Najibi, Mohammad Amin Ghiasi, Zheng Xu, John Dickerson, Christoph Studer +3

NeurIPS 2019poster

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, the high cost of generating strong adversarial examples makes standard adversarial training impractical on large-scale pr…

Cited by 1720 Source ↗PDF ↗Scholar ↗

2019

Are adversarial examples inevitable?

Ali Shafahi, W. Ronny Huang, Christoph Studer, Soheil Feizi, Tom Goldstein

ICLR 2019poster

A wide range of defenses have been proposed to harden neural networks against adversarial attacks. However, a pattern has emerged in which the majority of adversarial defenses are quickly broken by new attacks. Given the lack of success at generating robust defenses, we are led to ask a fundamental…

Cited by 392 Source ↗PDF ↗Scholar ↗

2018

Poison Frogs! Targeted Clean-Label Poisoning Attacks on Neural Networks

Ali Shafahi, W. Ronny Huang, Mahyar Najibi, Octavian Suciu, Christoph Studer, Tudor Dumitras +1

NeurIPS 2018poster

Data poisoning is an attack on machine learning models wherein the attacker adds examples to the training set to manipulate the behavior of the model at test time. This paper explores poisoning attacks on neural nets. The proposed attacks use ``clean-labels''; they don't require the attacker to have…

Cited by 1414 Source ↗PDF ↗code ↗Scholar ↗