137 citations · 266 across the 14 of their papers we have counts for
20 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…
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…
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…
Exploring Model Robustness with Adaptive Networks and Improved Adversarial Training
Zheng Xu, Ali Shafahi, Tom Goldstein
Adversarial training has proven to be effective in hardening networks against adversarial examples. However, the gained robustness is limited by network capacity and number of trai…
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…
WITCHcraft: Efficient PGD attacks with random step size
Ping-Yeh Chiang, Jonas Geiping, Micah Goldblum +4
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 wit…
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…
Adversarial attacks on Copyright Detection Systems
Parsa Saadatpanah, Ali Shafahi, Tom Goldstein
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 pa…
Transferable Clean-Label Poisoning Attacks on Deep Neural Nets
Chen Zhu, W. Ronny Huang, Ali Shafahi +4
Clean-label poisoning attacks inject innocuous looking (and "correctly" labeled) poison images into training data, causing a model to misclassify a targeted image after being train…
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…
Universal Adversarial Training
Ali Shafahi, Mahyar Najibi, Zheng Xu +3
Standard adversarial attacks change the predicted class label of a selected image by adding specially tailored small perturbations to its pixels. In contrast, a universal perturbat…
Are adversarial examples inevitable?
Ali Shafahi, W. Ronny Huang, Christoph Studer +2
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…
A matching-based heuristic algorithm for school bus routing problems
Ali Shafahi, Zhongxiang Wang, Ali Haghani
School bus planning problem (SBPP) has drawn much research attention due to the huge costs of school transportation. In the literature, the SBPP is usually decomposed into the rout…
Poison Frogs! Targeted Clean-Label Poisoning Attacks on Neural Networks
Ali Shafahi, W. Ronny Huang, Mahyar Najibi +4
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 explo…
School bus routing by maximizing trip compatibility
Ali Shafahi, Zhongxiang Wang, Ali Haghani
School bus planning is usually divided into routing and scheduling due to the complexity of solving them concurrently. However, the separation between these two steps may lead to w…
SCDA: School Compatibility Decomposition Algorithm for Solving the Multi-School Bus Routing and Scheduling Problem
Zhongxiang Wang, Ali Shafahi, Ali Haghani
Safely serving the school transportation demand with the minimum number of buses is one of the highest financial goals of school transportation directors. To achieve that objective…
Understanding and Visualizing the District of Columbia Capital Bikeshare System Using Data Analysis for Balancing Purposes
Kiana Roshan Zamir, Ali Shafahi, Ali Haghani
Bike sharing systems' popularity has consistently been rising during the past years. Managing and maintaining these emerging systems are indispensable parts of these systems. Visua…
Balanced scheduling of school bus trips using a perfect matching heuristic
Ali Shafahi, Sanaz Aliari, Ali Haghani
In the school bus scheduling problem, the main contributing factor to the cost is the number of buses needed for the operations. However, in the case of subcontracting the transpor…
Stochastic Emergency Response Units (ERUs) Allocation Considering Secondary Incident Occurrences
Hyoshin Park, Ali Shafahi, Ali Haghani
Location of depots and routing of emergency response units are assumed to be interdependent in the incident management system. System costs will be excessive if delay regarding rou…