相关论文: Predictive Response Optimization: Using Reinforcem…

Norms are behavioral expectations in communities. Online communities are also expected to abide by the rules and regulations that are expressed in the code of conduct of a system. Even though community authorities continuously prompt their…

Deep learning models have recently become popular for detecting malicious user activity sessions in computing platforms. In many real-world scenarios, only a few labeled malicious and a large amount of normal sessions are available. These…

Online social networks (OSNs) are increasingly threatened by social bots which are software-controlled OSN accounts that mimic human users with malicious intentions. A social botnet refers to a group of social bots under the control of a…

This work tackles the problem of overoptimization in reinforcement learning from human feedback (RLHF), a prevalent technique for aligning models with human preferences. RLHF relies on reward or preference models trained on \emph{fixed…

The presence of offensive language on social media platforms and the implications this poses is becoming a major concern in modern society. Given the enormous amount of content created every day, automatic methods are required to detect and…

Training practical agents usually involve offline and online reinforcement learning (RL) to balance the policy's performance and interaction costs. In particular, online fine-tuning has become a commonly used method to correct the erroneous…

Online abusive behavior affects millions and the NLP community has attempted to mitigate this problem by developing technologies to detect abuse. However, current methods have largely focused on a narrow definition of abuse to detriment of…

Social networks are frequently polluted by rumors, which can be detected by advanced models such as graph neural networks. However, the models are vulnerable to attacks and understanding the vulnerabilities is critical to rumor detection in…

Numerous algorithms have been proposed to $\textit{align}$ language models to remove undesirable behaviors. However, the challenges associated with a very large state space and creating a proper reward function often result in various…

The pervasive use of social media platforms, such as Facebook, Instagram, and X, has significantly amplified our electronic interconnectedness. Moreover, these platforms are now easily accessible from any location at any given time.…

[Context] Researchers analyze underground forums to study abuse and cybercrime activities. Due to the size of the forums and the domain expertise required to identify criminal discussions, most approaches employ supervised machine learning…

This dissertation investigates how reinforcement learning (RL) methods can be designed to be safe, sample-efficient, and robust. Framed through the unifying perspective of contextual-bandit RL, the work addresses two major application…

In this paper, we describe a new algorithm called Preferential Attachment k-class Classifier (PreAttacK) for detecting fake accounts in a social network. Recently, several algorithms have obtained high accuracy on this problem. However,…

In the United States and elsewhere, risk assessment algorithms are being used to help inform criminal justice decision-makers. A common intent is to forecast an offender's ``future dangerousness.'' Such algorithms have been correctly…

Adversarial attacks have been shown to be highly effective at degrading the performance of deep neural networks (DNNs). The most prominent defense is adversarial training, a method for learning a robust model. Nevertheless, adversarial…

Online Social Networks (OSNs) have come to play an increasingly important role in our social lives, and their inherent privacy problems have become a major concern for users. Can we assist consumers in their privacy decision-making…

Most provably-efficient learning algorithms introduce optimism about poorly-understood states and actions to encourage exploration. We study an alternative approach for efficient exploration, posterior sampling for reinforcement learning…

In this paper, we study oracle-efficient algorithms for beyond worst-case analysis of online learning. We focus on two settings. First, the smoothed analysis setting of [RST11,HRS22] where an adversary is constrained to generating samples…

Deep reinforcement learning has achieved impressive successes yet often requires a very large amount of interaction data. This result is perhaps unsurprising, as using complicated function approximation often requires more data to fit, and…

Safe reinforcement learning (Safe RL) refers to a class of techniques that aim to prevent RL algorithms from violating constraints in the process of decision-making and exploration during trial and error. In this paper, a novel model-free…