相关论文: Harder to Defend: Towards Chinese Toxicity Attacks…

Existing Chinese toxic content detection methods mainly target sentence-level classification but often fail to provide readable and contiguous toxic evidence spans. We propose \textbf{ToxiTrace}, an explainability-oriented method for…

The open-endedness of large language models (LLMs) combined with their impressive capabilities may lead to new safety issues when being exploited for malicious use. While recent studies primarily focus on probing toxic outputs that can be…

Detecting toxic content using language models is important but challenging. While large language models (LLMs) have demonstrated strong performance in understanding Chinese, recent studies show that simple character substitutions in toxic…

Unnatural text correction aims to automatically detect and correct spelling errors or adversarial perturbation errors in sentences. Existing methods typically rely on fine-tuning or adversarial training to correct errors, which have…

When Large Language Models (LLMs) are deployed in Chinese-language settings, a troubling pattern emerges: safety systems that work well in English break down. These systems struggle to cross linguistic and cultural bound-aries, leaving…

Large Language Models (LLMs) have achieved remarkable success across domains such as healthcare, education, and cybersecurity. However, this openness also introduces significant security risks, particularly through embedding space…

The volume of machine-generated content online has grown dramatically due to the widespread use of Large Language Models (LLMs), leading to new challenges for content moderation systems. Conventional content moderation classifiers, which…

Large language models (LLMs) remain vulnerable to jailbreaking attacks despite their impressive capabilities. Investigating these weaknesses is crucial for robust safety mechanisms. Existing attacks primarily distract LLMs by introducing…

Despite extensive diagnostics and debugging by developers, AI systems sometimes exhibit harmful unintended behaviors. Finding and fixing these is challenging because the attack surface is so large -- it is not tractable to exhaustively…

Many studies have demonstrated that large language models (LLMs) can produce harmful responses, exposing users to unexpected risks when LLMs are deployed. Previous studies have proposed comprehensive taxonomies of the risks posed by LLMs,…

Large language models (LLMs) excel in text understanding and generation but raise significant safety and ethical concerns in high-stakes applications. To mitigate these risks, we present Libra-Guard, a cutting-edge safeguard system designed…

Cyber Threat Intelligence (CTI) has emerged as a vital complementary approach that operates in the early phases of the cyber threat lifecycle. CTI involves collecting, processing, and analyzing threat data to provide a more accurate and…

Recent studies have revealed that NLP predictive models are vulnerable to adversarial attacks. Most existing studies focused on designing attacks to evaluate the robustness of NLP models in the English language alone. Literature has seen an…

Large language models (LLMs) are increasingly integrated into sensitive workflows, raising the stakes for adversarial robustness and safety. This paper introduces Transient Turn Injection(TTI), a new multi-turn attack technique that…

The proliferation of hate speech has inflicted significant societal harm, with its intensity and directionality closely tied to specific targets and arguments. In recent years, numerous machine learning-based methods have been developed to…

Bidirectional Encoder Representations from Transformers (BERT) have shown to be a promising way to dramatically improve the performance across various Natural Language Processing tasks [Devlin et al., 2019]. Meanwhile, progress made over…

Large language models (LLMs) are often fine-tuned on uncurated text datasets that adversaries can poison. Existing poisoning attacks primarily rely on fixed trigger phrases that defenses such as outlier detection, clean-data regularization,…

Despite of the superb performance on a wide range of tasks, pre-trained language models (e.g., BERT) have been proved vulnerable to adversarial texts. In this paper, we present RoChBERT, a framework to build more Robust BERT-based models by…

Transformer-based text classifiers such as BERT, RoBERTa, T5, and GPT have shown strong performance in natural language processing tasks but remain vulnerable to adversarial examples. These vulnerabilities raise significant security…

Recent NLP literature pays little attention to the robustness of toxicity language predictors, while these systems are most likely to be used in adversarial contexts. This paper presents a novel adversarial attack, \texttt{ToxicTrap},…