Search Results for author:
Found 18 papers, 10 papers with code
Coercing LLMs to do and reveal (almost) anything
It has recently been shown that adversarial attacks on large language models (LLMs) can "jailbreak" the model into making harmful statements.
Shadowcast: Stealthy Data Poisoning Attacks Against Vision-Language Models
We show that Shadowcast are highly effective in achieving attacker's intentions using as few as 50 poison samples.
Battle of the Backbones: A Large-Scale Comparison of Pretrained Models across Computer Vision Tasks
Battle of the Backbones (BoB) makes this choice easier by benchmarking a diverse suite of pretrained models, including vision-language models, those trained via self-supervised learning, and the Stable Diffusion backbone, across a diverse set of computer vision tasks ranging from classification to object detection to OOD generalization and more.
On the Exploitability of Instruction Tuning
In this work, we investigate how an adversary can exploit instruction tuning by injecting specific instruction-following examples into the training data that intentionally changes the model's behavior.
Bring Your Own Data! Self-Supervised Evaluation for Large Language Models
With the rise of Large Language Models (LLMs) and their ubiquitous deployment in diverse domains, measuring language model behavior on realistic data is imperative.
On the Reliability of Watermarks for Large Language Models
We also consider a range of new detection schemes that are sensitive to short spans of watermarked text embedded inside a large document, and we compare the robustness of watermarking to other kinds of detectors.
Model-Agnostic Hierarchical Attention for 3D Object Detection
By plugging our proposed modules into the state-of-the-art transformer-based 3D detector, we improve the previous best results on both benchmarks, with the largest improvement margin on small objects.
What do Vision Transformers Learn? A Visual Exploration
In addition, we show that ViTs maintain spatial information in all layers except the final layer.
Test-Time Prompt Tuning for Zero-Shot Generalization in Vision-Language Models
In evaluating cross-dataset generalization with unseen categories, TPT performs on par with the state-of-the-art approaches that use additional training data.
Gradient-Free Adversarial Training Against Image Corruption for Learning-based Steering
We introduce a simple yet effective framework for improving the robustness of learning algorithms against image corruptions for autonomous driving.
Contrastive Learning is Just Meta-Learning
Contrastive learning has recently taken off as a paradigm for learning from unlabeled data.
Where do Models go Wrong? Parameter-Space Saliency Maps for Explainability
We find that samples which cause similar parameters to malfunction are semantically similar.
Improving Robustness of Learning-based Autonomous Steering Using Adversarial Images
For safety of autonomous driving, vehicles need to be able to drive under various lighting, weather, and visibility conditions in different environments.
Driving through the Lens: Improving Generalization of Learning-based Steering using Simulated Adversarial Examples
To ensure the wide adoption and safety of autonomous driving, the vehicles need to be able to drive under various lighting, weather, and visibility conditions in different environments.
Towards Accurate Quantization and Pruning via Data-free Knowledge Transfer
Further, we demonstrate that the compact structure and corresponding initialization from the Lottery Ticket Hypothesis can also help in data-free training.
Prepare for the Worst: Generalizing across Domain Shifts with Adversarial Batch Normalization
Adversarial training is the industry standard for producing models that are robust to small adversarial perturbations.
Encoding Robustness to Image Style via Adversarial Feature Perturbations
We adapt adversarial training by directly perturbing feature statistics, rather than image pixels, to produce models that are robust to various unseen distributional shifts.
Headless Horseman: Adversarial Attacks on Transfer Learning Models
We first demonstrate successful transfer attacks against a victim network using \textit{only} its feature extractor.
