78 citations · 273 across the 16 of their papers we have counts for
17 papers
RAG LLMs are Not Safer: A Safety Analysis of Retrieval-Augmented Generation for Large Language Models
Bang An, Shiyue Zhang, Mark Dredze
Efforts to ensure the safety of large language models (LLMs) include safety fine-tuning, evaluation, and red teaming. However, despite the widespread use of the Retrieval-Augmented…
Universal Pyramid Adversarial Training for Improved ViT Performance
Ping-yeh Chiang, Yipin Zhou, Omid Poursaeed +4
Recently, Pyramid Adversarial training (Herrmann et al., 2022) has been shown to be very effective for improving clean accuracy and distribution-shift robustness of vision transfor…
NEFTune: Noisy Embeddings Improve Instruction Finetuning
Neel Jain, Ping-yeh Chiang, Yuxin Wen +10
We show that language model finetuning can be improved, sometimes dramatically, with a simple augmentation. NEFTune adds noise to the embedding vectors during training. Standard fi…
Baseline Defenses for Adversarial Attacks Against Aligned Language Models
Neel Jain, Avi Schwarzschild, Yuxin Wen +7
As Large Language Models quickly become ubiquitous, it becomes critical to understand their security vulnerabilities. Recent work shows that text optimizers can produce jailbreakin…
K-SAM: Sharpness-Aware Minimization at the Speed of SGD
Renkun Ni, Ping-yeh Chiang, Jonas Geiping +3
Sharpness-Aware Minimization (SAM) has recently emerged as a robust technique for improving the accuracy of deep neural networks. However, SAM incurs a high computational cost in p…
Certified Neural Network Watermarks with Randomized Smoothing
Arpit Bansal, Ping-yeh Chiang, Michael Curry +5
Watermarking is a commonly used strategy to protect creators' rights to digital images, videos and audio. Recently, watermarking methods have been extended to deep learning models…
Active Learning at the ImageNet Scale
Zeyad Ali Sami Emam, Hong-Min Chu, Ping-Yeh Chiang +4
Active learning (AL) algorithms aim to identify an optimal subset of data for annotation, such that deep neural networks (DNN) can achieve better performance when trained on this l…
Adversarial Examples Make Strong Poisons
Liam Fowl, Micah Goldblum, Ping-yeh Chiang +3
The adversarial machine learning literature is largely partitioned into evasion attacks on testing data and poisoning attacks on training data. In this work, we show that adversari…
Preventing Unauthorized Use of Proprietary Data: Poisoning for Secure Dataset Release
Liam Fowl, Ping-yeh Chiang, Micah Goldblum +4
Large organizations such as social media companies continually release data, for example user images. At the same time, these organizations leverage their massive corpora of releas…
ProportionNet: Balancing Fairness and Revenue for Auction Design with Deep Learning
Kevin Kuo, Anthony Ostuni, Elizabeth Horishny +5
The design of revenue-maximizing auctions with strong incentive guarantees is a core concern of economic theory. Computational auctions enable online advertising, sourcing, spectru…
WrapNet: Neural Net Inference with Ultra-Low-Resolution Arithmetic
Renkun Ni, Hong-min Chu, Oscar Castañeda +3
Low-resolution neural networks represent both weights and activations with few bits, drastically reducing the multiplication complexity. Nonetheless, these products are accumulated…
Detection as Regression: Certified Object Detection by Median Smoothing
Ping-yeh Chiang, Michael J. Curry, Ahmed Abdelkader +3
Despite the vulnerability of object detectors to adversarial attacks, very few defenses are known to date. While adversarial training can improve the empirical robustness of image…
Certifying Strategyproof Auction Networks
Michael J. Curry, Ping-Yeh Chiang, Tom Goldstein +1
Optimal auctions maximize a seller's expected revenue subject to individual rationality and strategyproofness for the buyers. Myerson's seminal work in 1981 settled the case of auc…
Certified Defenses for Adversarial Patches
Ping-Yeh Chiang, Renkun Ni, Ahmed Abdelkader +3
Adversarial patch attacks are among one of the most practical threat models against real-world computer vision systems. This paper studies certified and empirical defenses against…
Improving the Tightness of Convex Relaxation Bounds for Training Certifiably Robust Classifiers
Chen Zhu, Renkun Ni, Ping-yeh Chiang +3
Convex relaxations are effective for training and certifying neural networks against norm-bounded adversarial attacks, but they leave a large gap between certifiable and empirical…
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…
Compressing GANs using Knowledge Distillation
Angeline Aguinaldo, Ping-Yeh Chiang, Alex Gain +3
Generative Adversarial Networks (GANs) have been used in several machine learning tasks such as domain transfer, super resolution, and synthetic data generation. State-of-the-art G…