相关论文: Counter-Empirical Attacking based on Adversarial R…

Despite significant progress in designing powerful adversarial evasion attacks for robustness verification, the evaluation of these methods often remains inconsistent and unreliable. Many assessments rely on mismatched models, unverified…

We study reinforcement learning from human feedback in general Markov decision processes, where agents learn from trajectory-level preference comparisons. A central challenge in this setting is to design algorithms that select informative…

We introduce the paradigm of adversarial attacks that target the dynamics of Complex Adaptive Systems (CAS). To facilitate the analysis of such attacks, we present multiple approaches to the modeling of CAS as dynamical, data-driven, and…

Temporal-Difference (TD) learning is a standard and very successful reinforcement learning approach, at the core of both algorithms that learn the value of a given policy, as well as algorithms which learn how to improve policies.…

While multi-agent LLM systems show strong capabilities in various domains, they are highly vulnerable to adversarial and low-performing agents. To resolve this issue, in this paper, we introduce a general and adversary-resistant multi-agent…

Neural Networks (NNs) are vulnerable to adversarial examples. Such inputs differ only slightly from their benign counterparts yet provoke misclassifications of the attacked NNs. The required perturbations to craft the examples are often…

Machine learning models using transaction records as inputs are popular among financial institutions. The most efficient models use deep-learning architectures similar to those in the NLP community, posing a challenge due to their…

This study investigates behavior-targeted attacks on reinforcement learning and their countermeasures. Behavior-targeted attacks aim to manipulate the victim's behavior as desired by the adversary through adversarial interventions in state…

Recently, a series of pioneer studies have shown the potency of pre-trained models in sequential recommendation, illuminating the path of building an omniscient unified pre-trained recommendation model for different downstream…

Machine learning researchers have long noticed the phenomenon that the model training process will be more effective and efficient when the training samples are densely sampled around the underlying decision boundary. While this observation…

Adversarial examples can be defined as inputs to a model which induce a mistake - where the model output is different than that of an oracle, perhaps in surprising or malicious ways. Original models of adversarial attacks are primarily…

Characterizing the reputation of an evaluator is particularly significant for consumer to obtain useful information from online rating systems. Furthermore, to overcome the difficulties with spam attacks on the rating system and to get the…

Reinforcement learning algorithms describe how an agent can learn an optimal action policy in a sequential decision process, through repeated experience. In a given environment, the agent policy provides him some running and terminal…

Adversarial training (AT) with imperfect supervision is significant but receives limited attention. To push AT towards more practical scenarios, we explore a brand new yet challenging setting, i.e., AT with complementary labels (CLs), which…

Fairness is becoming a rising concern w.r.t. machine learning model performance. Especially for sensitive fields such as criminal justice and loan decision, eliminating the prediction discrimination towards a certain group of population…

Reinforcement learning is well suited for optimizing policies of recommender systems. Current solutions mostly focus on model-free approaches, which require frequent interactions with the real environment, and thus are expensive in model…

This study examines vulnerabilities in transformer-based automated short-answer grading systems used in medical education, with a focus on how these systems can be manipulated through adversarial gaming strategies. Our research identifies…

Deep neural networks are vulnerable to adversarial examples, which poses security concerns on these algorithms due to the potentially severe consequences. Adversarial attacks serve as an important surrogate to evaluate the robustness of…

This paper presents a framework which enables a user to more easily make corrections to adversarial texts. While attack algorithms have been demonstrated to automatically build adversaries, changes made by the algorithms can often have poor…

Classification algorithms based on Artificial Intelligence (AI) are nowadays applied in high-stakes decisions in finance, healthcare, criminal justice, or education. Individuals can strategically adapt to the information gathered about…