Related papers: Adversarial Preference Learning for Robust LLM Ali…

Inverse Reinforcement Learning (IRL) learns an optimal policy, given some expert demonstrations, thus avoiding the need for the tedious process of specifying a suitable reward function. However, current methods are constrained by at least…

The complexity of designing reward functions has been a major obstacle to the wide application of deep reinforcement learning (RL) techniques. Describing an agent's desired behaviors and properties can be difficult, even for experts. A new…

As automatic speech recognition (ASR) systems are now being widely deployed in the wild, the increasing threat of adversarial attacks raises serious questions about the security and reliability of using such systems. On the other hand,…

Most of the existing generative adversarial networks (GAN) for text generation suffer from the instability of reinforcement learning training algorithms such as policy gradient, leading to unstable performance. To tackle this problem, we…

Reward models (RMs) play a pivotal role in aligning large language models (LLMs) with human preferences. However, traditional RM training, which relies on response pairs tied to specific prompts, struggles to disentangle prompt-driven…

This paper presents a holistic approach to attacker preference modeling from system-level audit logs using inverse reinforcement learning (IRL). Adversary modeling is an important capability in cybersecurity that lets defenders characterize…

Recently, robust reinforcement learning (RL) methods against input observation have garnered significant attention and undergone rapid evolution due to RL's potential vulnerability. Although these advanced methods have achieved reasonable…

Deep neural networks are vulnerable to adversarial noise. Adversarial Training (AT) has been demonstrated to be the most effective defense strategy to protect neural networks from being fooled. However, we find AT omits to learning robust…

Recent advancements in open-domain dialogue systems have been propelled by the emergence of high-quality large language models (LLMs) and various effective training methodologies. Nevertheless, the presence of toxicity within these models…

Despite the remarkable performance of deep neural networks on various computer vision tasks, they are known to be susceptible to adversarial perturbations, which makes it challenging to deploy them in real-world safety-critical…

Ensuring Large Language Models (LLMs) align with diverse human preferences while preserving privacy and fairness remains a challenge. Existing methods, such as Reinforcement Learning from Human Feedback (RLHF), rely on centralized data…

Although deep neural networks have achieved super-human performance on many classification tasks, they often exhibit a worrying lack of robustness towards adversarially generated examples. Thus, considerable effort has been invested into…

Model-based reinforcement learning has attracted much attention due to its high sample efficiency and is expected to be applied to real-world robotic applications. In the real world, as unobservable disturbances can lead to unexpected…

Adversarial representation learning aims to learn data representations for a target task while removing unwanted sensitive information at the same time. Existing methods learn model parameters iteratively through stochastic gradient…

With the recent advancements in machine learning (ML), numerous ML-based approaches have been extensively applied in software analytics tasks to streamline software development and maintenance processes. Nevertheless, studies indicate that…

Attributing APT (Advanced Persistent Threat) malware to their respective groups is crucial for threat intelligence and cybersecurity. However, APT adversaries often conceal their identities, rendering attribution inherently adversarial.…

Direct Preference Optimization (DPO) has emerged as an important approach for learning from human preferences in aligning large language models (LLMs). However, collecting human preference data is costly and inefficient, motivating methods…

Modern action-conditioned video world models achieve strong short-horizon visual realism, yet remain unreliable on rare, interaction-critical transitions that dominate downstream planning and policy performance. Because passive…

Reinforcement Learning from Human Feedback (RLHF) is a powerful paradigm for aligning foundation models to human values and preferences. However, current RLHF techniques cannot account for the naturally occurring differences in individual…

Real-world training data is often noisy; for example, human annotators assign conflicting class labels to the same instances. Partial-label learning (PLL) is a weakly supervised learning paradigm that allows training classifiers in this…