Related papers: Attack-in-the-Chain: Bootstrapping Large Language …
Large reasoning models (LRMs) have achieved impressive performance in complex tasks, often outperforming conventional large language models (LLMs). However, the prevalent issue of overthinking severely limits their computational efficiency.…
Recommender systems are tasked to infer users' evolving preferences and rank items aligned with their intents, which calls for in-depth reasoning beyond pattern-based scoring. Recent efforts start to leverage large language models (LLMs)…
Neural ranking models (NRMs) achieve strong retrieval effectiveness, yet prior work has shown they are vulnerable to adversarial perturbations. We revisit this robustness question with a minimal, query-aware attack that promotes a target…
We study an important task of attacking natural language processing models in a black box setting. We propose an attack strategy that crafts semantically similar adversarial examples on text classification and entailment tasks. Our proposed…
Large Language Models (LLMs) have gradually become the gateway for people to acquire new knowledge. However, attackers can break the model's security protection ("jail") to access restricted information, which is called "jailbreaking."…
Training Large Language Models (LLMs) for chain-of-thought reasoning presents a significant challenge: supervised fine-tuning on a single "golden" rationale hurts generalization as it penalizes equally valid alternatives, whereas…
We study an important and challenging task of attacking natural language processing models in a hard label black box setting. We propose a decision-based attack strategy that crafts high quality adversarial examples on text classification…
This position paper proposes a novel approach to advancing NLP security by leveraging Large Language Models (LLMs) as engines for generating diverse adversarial attacks. Building upon recent work demonstrating LLMs' effectiveness in…
Neural ranking models (NRMs) have achieved promising results in information retrieval. NRMs have also been shown to be vulnerable to adversarial examples. A typical Word Substitution Ranking Attack (WSRA) against NRMs was proposed recently,…
Malicious URL classification represents a crucial aspect of cyber security. Although existing work comprises numerous machine learning and deep learning-based URL classification models, most suffer from generalisation and domain-adaptation…
Large language models (LLMs) show strong performance across many applications, but their ability to memorize and potentially reveal training data raises serious privacy concerns. We introduce the PopQuiz Attack, a black-box membership…
Large Reasoning Models (LRMs) significantly improve the reasoning ability of Large Language Models (LLMs) by learning to reason, exhibiting promising performance in solving complex tasks. However, their deliberative reasoning process leads…
Security vulnerabilities are increasingly prevalent in modern software and they are widely consequential to our society. Various approaches to defending against these vulnerabilities have been proposed, among which those leveraging deep…
Large language models (LLMs) have achieved remarkable performance in various natural language processing tasks, especially in dialogue systems. However, LLM may also pose security and moral threats, especially in multi round conversations…
Large Language Models (LLMs) have demonstrated remarkable capabilities in various tasks. However, they remain exposed to jailbreak attacks, eliciting harmful responses. The nested scenario strategy has been increasingly adopted across…
Emerging Large Reasoning Models (LRMs) consistently excel in mathematical and reasoning tasks, showcasing remarkable capabilities. However, the enhancement of reasoning abilities and the exposure of internal reasoning processes introduce…
Deep neural networks are susceptible to adversarial inputs and various methods have been proposed to defend these models against adversarial attacks under different perturbation models. The robustness of models to adversarial attacks has…
This work considers a black-box threat model in which adversaries attempt to propagate arbitrary non-relevant content in search. We show that retrievers, rerankers, and LLM relevance judges are all highly vulnerable to attacks that enable…
Neural text ranking models have witnessed significant advancement and are increasingly being deployed in practice. Unfortunately, they also inherit adversarial vulnerabilities of general neural models, which have been detected but remain…
Large Language Models (LLMs) have achieved remarkable success in tasks requiring complex reasoning, such as code generation, mathematical problem solving, and algorithmic synthesis -- especially when aided by reasoning tokens and…