activity
20192026
most citedBattle of the Backbones: A Large-Scale Comparison of Pretrained Models across Computer Vision Tasks

26 citations · 54 across the 9 of their papers we have counts for

collaborators
Showing cs.LGShow all

7 papers · 1 filter

cs.LG2024

Generating Potent Poisons and Backdoors from Scratch with Guided Diffusion

Hossein Souri, Arpit Bansal, Hamid Kazemi +7

Modern neural networks are often trained on massive datasets that are web scraped with minimal human inspection. As a result of this insecure curation pipeline, an adversary can po…

cs.LG2022★ 6 cited

Thinking Two Moves Ahead: Anticipating Other Users Improves Backdoor Attacks in Federated Learning

Yuxin Wen, Jonas Geiping, Liam Fowl +4

Federated learning is particularly susceptible to model poisoning and backdoor attacks because individual users have direct control over the training data and model updates. At the…

cs.LG2022★ 8 cited

Pre-Train Your Loss: Easy Bayesian Transfer Learning with Informative Priors

Ravid Shwartz-Ziv, Micah Goldblum, Hossein Souri +4

Deep learning is increasingly moving towards a transfer learning paradigm whereby large foundation models are fine-tuned on downstream tasks, starting from an initialization learne…

cs.LG2021

Mutual Adversarial Training: Learning together is better than going alone

Jiang Liu, Chun Pong Lau, Hossein Souri +2

Recent studies have shown that robustness to adversarial attacks can be transferred across networks. In other words, we can make a weak model more robust with the help of a strong…

cs.LG2021★ 1 cited

Identification of Attack-Specific Signatures in Adversarial Examples

Hossein Souri, Pirazh Khorramshahi, Chun Pong Lau +2

The adversarial attack literature contains a myriad of algorithms for crafting perturbations which yield pathological behavior in neural networks. In many cases, multiple algorithm…

cs.LG2021

Sleeper Agent: Scalable Hidden Trigger Backdoors for Neural Networks Trained from Scratch

Hossein Souri, Liam Fowl, Rama Chellappa +2

As the curation of data for machine learning becomes increasingly automated, dataset tampering is a mounting threat. Backdoor attackers tamper with training data to embed a vulnera…