22 citations · 77 across the 17 of their papers we have counts for
17 papers
Private Fine-tuning of Large Language Models with Zeroth-order Optimization
Xinyu Tang, Ashwinee Panda, Milad Nasr +2
Differentially private stochastic gradient descent (DP-SGD) allows models to be trained in a privacy-preserving manner, but has proven difficult to scale to the era of foundation m…
A Randomized Approach for Tight Privacy Accounting
Jiachen T. Wang, Saeed Mahloujifar, Tong Wu +2
Bounding privacy leakage over compositions, i.e., privacy accounting, is a key challenge in differential privacy (DP). The privacy parameter ($\eps$ or ) is often easy to estima…
Uncovering Adversarial Risks of Test-Time Adaptation
Tong Wu, Feiran Jia, Xiangyu Qi +4
Recently, test-time adaptation (TTA) has been proposed as a promising solution for addressing distribution shifts. It allows a base model to adapt to an unforeseen distribution dur…
MultiRobustBench: Benchmarking Robustness Against Multiple Attacks
Sihui Dai, Saeed Mahloujifar, Chong Xiang +3
The bulk of existing research in defending against adversarial examples focuses on defending against a single (typically bounded Lp-norm) attack, but for a practical setting, machi…
Bounding Training Data Reconstruction in DP-SGD
Jamie Hayes, Saeed Mahloujifar, Borja Balle
Differentially private training offers a protection which is usually interpreted as a guarantee against membership inference attacks. By proxy, this guarantee extends to other thre…
A New Linear Scaling Rule for Private Adaptive Hyperparameter Optimization
Ashwinee Panda, Xinyu Tang, Saeed Mahloujifar +2
An open problem in differentially private deep learning is hyperparameter optimization (HPO). DP-SGD introduces new hyperparameters and complicates existing ones, forcing researche…
Renyi Differential Privacy of Propose-Test-Release and Applications to Private and Robust Machine Learning
Jiachen T. Wang, Saeed Mahloujifar, Shouda Wang +2
Propose-Test-Release (PTR) is a differential privacy framework that works with local sensitivity of functions, instead of their global sensitivity. This framework is typically used…
Just Rotate it: Deploying Backdoor Attacks via Rotation Transformation
Tong Wu, Tianhao Wang, Vikash Sehwag +2
Recent works have demonstrated that deep learning models are vulnerable to backdoor poisoning attacks, where these attacks instill spurious correlations to external trigger pattern…
Towards A Proactive ML Approach for Detecting Backdoor Poison Samples
Xiangyu Qi, Tinghao Xie, Jiachen T. Wang +3
Adversaries can embed backdoors in deep learning models by introducing backdoor poison samples into training datasets. In this work, we investigate how to detect such poison sample…
Circumventing Backdoor Defenses That Are Based on Latent Separability
Xiangyu Qi, Tinghao Xie, Yiming Li +2
Recent studies revealed that deep learning is susceptible to backdoor poisoning attacks. An adversary can embed a hidden backdoor into a model to manipulate its predictions by only…
Formulating Robustness Against Unforeseen Attacks
Sihui Dai, Saeed Mahloujifar, Prateek Mittal
Existing defenses against adversarial examples such as adversarial training typically assume that the adversary will conform to a specific or known threat model, such as p…
ObjectSeeker: Certifiably Robust Object Detection against Patch Hiding Attacks via Patch-agnostic Masking
Chong Xiang, Alexander Valtchanov, Saeed Mahloujifar +1
Object detectors, which are widely deployed in security-critical systems such as autonomous vehicles, have been found vulnerable to patch hiding attacks. An attacker can use a sing…
SparseFed: Mitigating Model Poisoning Attacks in Federated Learning with Sparsification
Ashwinee Panda, Saeed Mahloujifar, Arjun N. Bhagoji +2
Federated learning is inherently vulnerable to model poisoning attacks because its decentralized nature allows attackers to participate with compromised devices. In model poisoning…
Mitigating Membership Inference Attacks by Self-Distillation Through a Novel Ensemble Architecture
Xinyu Tang, Saeed Mahloujifar, Liwei Song +4
Membership inference attacks are a key measure to evaluate privacy leakage in machine learning (ML) models. These attacks aim to distinguish training members from non-members by ex…
Parameterizing Activation Functions for Adversarial Robustness
Sihui Dai, Saeed Mahloujifar, Prateek Mittal
Deep neural networks are known to be vulnerable to adversarially perturbed inputs. A commonly used defense is adversarial training, whose performance is influenced by model capacit…
PatchCleanser: Certifiably Robust Defense against Adversarial Patches for Any Image Classifier
Chong Xiang, Saeed Mahloujifar, Prateek Mittal
The adversarial patch attack against image classification models aims to inject adversarially crafted pixels within a restricted image region (i.e., a patch) for inducing model mis…
Robust Learning Meets Generative Models: Can Proxy Distributions Improve Adversarial Robustness?
Vikash Sehwag, Saeed Mahloujifar, Tinashe Handina +4
While additional training data improves the robustness of deep neural networks against adversarial examples, it presents the challenge of curating a large number of specific real-w…