37 citations · 110 across the 9 of their papers we have counts for
12 papers
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…
Spotting LLMs With Binoculars: Zero-Shot Detection of Machine-Generated Text
Abhimanyu Hans, Avi Schwarzschild, Valeriia Cherepanova +5
Detecting text generated by modern large language models is thought to be hard, as both LLMs and humans can exhibit a wide range of complex behaviors. However, we find that a score…
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…
Bring Your Own Data! Self-Supervised Evaluation for Large Language Models
Neel Jain, Khalid Saifullah, Yuxin Wen +6
With the rise of Large Language Models (LLMs) and their ubiquitous deployment in diverse domains, measuring language model behavior on realistic data is imperative. For example, a…
Revisiting Image Classifier Training for Improved Certified Robust Defense against Adversarial Patches
Aniruddha Saha, Shuhua Yu, Arash Norouzzadeh +2
Certifiably robust defenses against adversarial patches for image classifiers ensure correct prediction against any changes to a constrained neighborhood of pixels. PatchCleanser a…
On the Reliability of Watermarks for Large Language Models
John Kirchenbauer, Jonas Geiping, Yuxin Wen +7
As LLMs become commonplace, machine-generated text has the potential to flood the internet with spam, social media bots, and valueless content. Watermarking is a simple and effecti…
Backdoor Attacks on Vision Transformers
Akshayvarun Subramanya, Aniruddha Saha, Soroush Abbasi Koohpayegani +2
Vision Transformers (ViT) have recently demonstrated exemplary performance on a variety of vision tasks and are being used as an alternative to CNNs. Their design is based on a sel…
Backdoor Attacks on Self-Supervised Learning
Aniruddha Saha, Ajinkya Tejankar, Soroush Abbasi Koohpayegani +1
Large-scale unlabeled data has spurred recent progress in self-supervised learning methods that learn rich visual representations. State-of-the-art self-supervised methods for lear…
Role of Spatial Context in Adversarial Robustness for Object Detection
Aniruddha Saha, Akshayvarun Subramanya, Koninika Patil +1
The benefits of utilizing spatial context in fast object detection algorithms have been studied extensively. Detectors increase inference speed by doing a single forward pass per i…
Hidden Trigger Backdoor Attacks
Aniruddha Saha, Akshayvarun Subramanya, Hamed Pirsiavash
With the success of deep learning algorithms in various domains, studying adversarial attacks to secure deep models in real world applications has become an important research topi…
Universal Litmus Patterns: Revealing Backdoor Attacks in CNNs
Soheil Kolouri, Aniruddha Saha, Hamed Pirsiavash +1
The unprecedented success of deep neural networks in many applications has made these networks a prime target for adversarial exploitation. In this paper, we introduce a benchmark…