相关论文: Counterfactual Evaluation for Blind Attack Detecti…

In an era where misinformation spreads freely, fact-checking (FC) plays a crucial role in verifying claims and promoting reliable information. While automated fact-checking (AFC) has advanced significantly, existing systems remain…

Counterfactual reasoning, a hallmark of intelligence, consists of three steps: inferring latent variables from observations (abduction), constructing alternatives (interventions), and predicting their outcomes (prediction). This skill is…

Despite the state-of-the-art performance of Large Language Models (LLMs), these models often suffer from hallucinations, which can undermine their performance in critical applications. In this work, we propose SAFE, a novel method for…

In recent years, Reward Machines (RMs) have stood out as a simple yet effective automata-based formalism for exposing and exploiting task structure in reinforcement learning settings. Despite their relevance, little to no attention has been…

Counterfactual explanations (CFEs) guide users on how to adjust inputs to machine learning models to achieve desired outputs. While existing research primarily addresses static scenarios, real-world applications often involve data or model…

In the domain of Privacy-Preserving Machine Learning (PPML), Fully Homomorphic Encryption (FHE) is often used for encrypted computation to allow secure and privacy-preserving outsourcing of machine learning modeling. While FHE enables…

The widespread adoption of code language models in software engineering tasks has exposed vulnerabilities to adversarial attacks, especially the identifier substitution attacks. Although existing identifier substitution attackers…

Modern code completion engines, powered by large language models (LLMs), assist millions of developers with their strong capabilities to generate functionally correct code. Due to this popularity, it is crucial to investigate the security…

Large Language Models (LLMs) are powerful zero-shot assessors used in real-world situations such as assessing written exams and benchmarking systems. Despite these critical applications, no existing work has analyzed the vulnerability of…

Backdoor attacks pose a significant threat to Large Language Models (LLMs), where adversaries can embed hidden triggers to manipulate LLM's outputs. Most existing defense methods, primarily designed for classification tasks, are ineffective…

Vision-Language Models (VLMs) often produce fluent Natural Language Explanations (NLEs) that sound convincing but may not reflect the causal factors driving predictions. This mismatch of plausibility and faithfulness poses technical and…

The security of Large Language Model (LLM) applications is fundamentally challenged by "form-first" attacks like prompt injection and jailbreaking, where malicious instructions are embedded within user inputs. Conventional defenses, which…

Modern face recognition systems remain vulnerable to spoofing attempts, including both physical presentation attacks and digital forgeries. Traditionally, these two attack vectors have been handled by separate models, each targeting its own…

Recent adversarial attack developments have made reinforcement learning more vulnerable, and different approaches exist to deploy attacks against it, where the key is how to choose the right timing of the attack. Some work tries to design…

Large Language Models (LLMs) presents significant priority in text understanding and generation. However, LLMs suffer from the risk of generating harmful contents especially while being employed to applications. There are several black-box…

Safety alignment approaches in large language models (LLMs) often lead to the over-refusal of benign queries, significantly diminishing their utility in sensitive scenarios. To address this challenge, we introduce FalseReject, a…

Reference-free evaluation metrics for grammatical error correction (GEC) have achieved high correlation with human judgments. However, these metrics are not designed to evaluate adversarial systems that aim to obtain unjustifiably high…

Face recognition (FR) systems have demonstrated outstanding verification performance, suggesting suitability for real-world applications ranging from photo tagging in social media to automated border control (ABC). In an advanced FR system…

Verifying the credibility of Cyber Threat Intelligence (CTI) is essential for reliable cybersecurity defense. However, traditional approaches typically treat this task as a static classification problem, relying on handcrafted features or…

As Large Language Models (LLMs) have risen in prominence over the past few years, there has been concern over the potential biases in LLMs inherited from the training data. Previous studies have examined how LLMs exhibit implicit bias, such…