Picture for Neal Mangaokar

Neal Mangaokar

PRP: Propagating Universal Perturbations to Attack Large Language Model Guard-Rails

Add code
Feb 24, 2024
Figure 1 for PRP: Propagating Universal Perturbations to Attack Large Language Model Guard-Rails
Figure 2 for PRP: Propagating Universal Perturbations to Attack Large Language Model Guard-Rails
Figure 3 for PRP: Propagating Universal Perturbations to Attack Large Language Model Guard-Rails
Figure 4 for PRP: Propagating Universal Perturbations to Attack Large Language Model Guard-Rails
Viaarxiv icon

Theoretically Principled Trade-off for Stateful Defenses against Query-Based Black-Box Attacks

Add code
Jul 30, 2023
Viaarxiv icon

Investigating Stateful Defenses Against Black-Box Adversarial Examples

Add code
Mar 17, 2023
Viaarxiv icon

Towards Adversarially Robust Deepfake Detection: An Ensemble Approach

Add code
Feb 11, 2022
Figure 1 for Towards Adversarially Robust Deepfake Detection: An Ensemble Approach
Figure 2 for Towards Adversarially Robust Deepfake Detection: An Ensemble Approach
Figure 3 for Towards Adversarially Robust Deepfake Detection: An Ensemble Approach
Figure 4 for Towards Adversarially Robust Deepfake Detection: An Ensemble Approach
Viaarxiv icon

Jekyll: Attacking Medical Image Diagnostics using Deep Generative Models

Add code
Apr 05, 2021
Figure 1 for Jekyll: Attacking Medical Image Diagnostics using Deep Generative Models
Figure 2 for Jekyll: Attacking Medical Image Diagnostics using Deep Generative Models
Figure 3 for Jekyll: Attacking Medical Image Diagnostics using Deep Generative Models
Figure 4 for Jekyll: Attacking Medical Image Diagnostics using Deep Generative Models
Viaarxiv icon

Deepfake Videos in the Wild: Analysis and Detection

Add code
Mar 11, 2021
Figure 1 for Deepfake Videos in the Wild: Analysis and Detection
Figure 2 for Deepfake Videos in the Wild: Analysis and Detection
Figure 3 for Deepfake Videos in the Wild: Analysis and Detection
Figure 4 for Deepfake Videos in the Wild: Analysis and Detection
Viaarxiv icon

T-Miner: A Generative Approach to Defend Against Trojan Attacks on DNN-based Text Classification

Add code
Mar 11, 2021
Figure 1 for T-Miner: A Generative Approach to Defend Against Trojan Attacks on DNN-based Text Classification
Figure 2 for T-Miner: A Generative Approach to Defend Against Trojan Attacks on DNN-based Text Classification
Figure 3 for T-Miner: A Generative Approach to Defend Against Trojan Attacks on DNN-based Text Classification
Figure 4 for T-Miner: A Generative Approach to Defend Against Trojan Attacks on DNN-based Text Classification
Viaarxiv icon