Related papers: Diffusion Guided Adversarial State Perturbations i…
Latent diffusion models have recently demonstrated superior capabilities in many downstream image synthesis tasks. However, customization of latent diffusion models using unauthorized data can severely compromise the privacy and…
Adversarial training for LLMs is one of the most promising methods to reliably improve robustness against adversaries. However, despite significant progress, models remain vulnerable to simple in-distribution exploits, such as rewriting…
Adversarial attacks that generate small L_p-norm perturbations to mislead classifiers have limited success in black-box settings and with unseen classifiers. These attacks are also not robust to defenses that use denoising filters and to…
Unrestricted adversarial attacks present a serious threat to deep learning models and adversarial defense techniques. They pose severe security problems for deep learning applications because they can effectively bypass defense mechanisms.…
We present a novel method of learning style-agnostic representation using both style transfer and adversarial learning in the reinforcement learning framework. The style, here, refers to task-irrelevant details such as the color of the…
This chapter studies emerging cyber-attacks on reinforcement learning (RL) and introduces a quantitative approach to analyze the vulnerabilities of RL. Focusing on adversarial manipulation on the cost signals, we analyze the performance…
Machine unlearning is a key defense mechanism for removing unauthorized concepts from text-to-image diffusion models, yet recent evidence shows that latent visual information often persists after unlearning. Existing adversarial approaches…
As agentic AI becomes more widespread, agents with distinct and possibly conflicting goals will interact in complex ways. These multi-agent interactions pose a fundamental challenge, particularly in social dilemmas, where agents' individual…
Deep reinforcement learning (DRL) algorithms can suffer from modeling errors between the simulation and the real world. Many studies use adversarial learning to generate perturbation during training process to model the discrepancy and…
Text-based reinforcement learning involves an agent interacting with a fictional environment using observed text and admissible actions in natural language to complete a task. Previous works have shown that agents can succeed in text-based…
Machine learning models are often trained on data from one distribution and deployed on others. So it becomes important to design models that are robust to distribution shifts. Most of the existing work focuses on optimizing for either…
Online reinforcement learning is becoming increasingly important for aligning diffusion models with non-differentiable objectives. However, existing methods still face limitations in assigning fine-grained credit along denoising…
Adversarial attacks can mislead deep learning models to make false predictions by implanting small perturbations to the original input that are imperceptible to the human eye, which poses a huge security threat to the computer vision…
Text-to-image diffusion models are a class of deep generative models that have demonstrated an impressive capacity for high-quality image generation. However, these models are susceptible to implicit biases that arise from web-scale…
Adversarial attacks, e.g., adversarial perturbations of the input and adversarial samples, pose significant challenges to machine learning and deep learning techniques, including interactive recommendation systems. The latent embedding…
Adversarial attacks on Natural Language Processing (NLP) models expose vulnerabilities by introducing subtle perturbations to input text, often leading to misclassification while maintaining human readability. Existing methods typically…
Recently, various auxiliary tasks have been proposed to accelerate representation learning and improve sample efficiency in deep reinforcement learning (RL). However, existing auxiliary tasks do not take the characteristics of RL problems…
Distributed diffusion is a powerful algorithm for multi-task state estimation which enables networked agents to interact with neighbors to process input data and diffuse information across the network. Compared to a centralized approach,…
The superiority of deep learning performance is threatened by safety issues for itself. Recent findings have shown that deep learning systems are very weak to adversarial examples, an attack form that was altered by the attacker's intent to…
Large language models (LLMs) are vulnerable to adversarial attacks that can elicit harmful responses. Defending against such attacks remains challenging due to the opacity of jailbreaking mechanisms and the high computational cost of…