Search Results for author:
Found 8 papers, 4 papers with code
PRP: Propagating Universal Perturbations to Attack Large Language Model Guard-Rails
More recent LLMs often incorporate an additional layer of defense, a Guard Model, which is a second LLM that is designed to check and moderate the output response of the primary LLM.
Theoretically Principled Trade-off for Stateful Defenses against Query-Based Black-Box Attacks
This work aims to address this gap by offering a theoretical characterization of the trade-off between detection and false positive rates for stateful defenses.
Stateful Defenses for Machine Learning Models Are Not Yet Secure Against Black-box Attacks
Such stateful defenses aim to defend against black-box attacks by tracking the query history and detecting and rejecting queries that are "similar" and thus preventing black-box attacks from finding useful gradients and making progress towards finding adversarial attacks within a reasonable query budget.
D4: Detection of Adversarial Diffusion Deepfakes Using Disjoint Ensembles
D4 uses an ensemble of models over disjoint subsets of the frequency spectrum to significantly improve adversarial robustness.
Jekyll: Attacking Medical Image Diagnostics using Deep Generative Models
The potential for fraudulent claims based on such generated 'fake' medical images is significant, and we demonstrate successful attacks on both X-rays and retinal fundus image modalities.
T-Miner: A Generative Approach to Defend Against Trojan Attacks on DNN-based Text Classification
T-Miner employs a sequence-to-sequence (seq-2-seq) generative model that probes the suspicious classifier and learns to produce text sequences that are likely to contain the Trojan trigger.
Deepfake Videos in the Wild: Analysis and Detection
AI-manipulated videos, commonly known as deepfakes, are an emerging problem.
GRAPHITE: Generating Automatic Physical Examples for Machine-Learning Attacks on Computer Vision Systems
We address three key requirements for practical attacks for the real-world: 1) automatically constraining the size and shape of the attack so it can be applied with stickers, 2) transform-robustness, i. e., robustness of a attack to environmental physical variations such as viewpoint and lighting changes, and 3) supporting attacks in not only white-box, but also black-box hard-label scenarios, so that the adversary can attack proprietary models.
