Related papers: TokenBreak: Bypassing Text Classification Models T…

This work introduces an approach to assessing phrase break in ESL learners' speech with pre-trained language models (PLMs). Different with traditional methods, this proposal converts speech to token sequences, and then leverages the power…

Tokenisation is the first step in almost all NLP tasks, and state-of-the-art transformer-based language models all use subword tokenisation algorithms to process input text. Existing algorithms have problems, often producing tokenisations…

It has recently been shown that adversarial attacks on large language models (LLMs) can "jailbreak" the model into making harmful statements. In this work, we argue that the spectrum of adversarial attacks on LLMs is much larger than merely…

While Large Language Models (LLMs) have shown significant advancements in performance, various jailbreak attacks have posed growing safety and ethical risks. Malicious users often exploit adversarial context to deceive LLMs, prompting them…

Large language models (LLMs) are widely adapted for downstream applications through fine-tuning, a process named customization. However, recent studies have identified a vulnerability during this process, where malicious samples can…

Large Language Models (LLMs) have transformed numerous fields by enabling advanced natural language interactions but remain susceptible to critical vulnerabilities, particularly jailbreak attacks. Current jailbreak techniques, while…

Large Language Models (LLMs) are known to be vulnerable to backdoor attacks, where triggers embedded in poisoned samples can maliciously alter LLMs' behaviors. In this paper, we move beyond attacking LLMs and instead examine backdoor…

Backdoor attack is a severe threat to the trustworthiness of DNN-based language models. In this paper, we first extend the definition of memorization of language models from sample-wise to more fine-grained sentence element-wise (e.g.,…

Large Language Models (LLMs) are susceptible to Jailbreaking attacks, which aim to extract harmful information by subtly modifying the attack query. As defense mechanisms evolve, directly obtaining harmful information becomes increasingly…

Machine learning based language models have recently made significant progress, which introduces a danger to spread misinformation. To combat this potential danger, several methods have been proposed for detecting text written by these…

Although Deep Neural Network (DNN) has led to unprecedented progress in various natural language processing (NLP) tasks, research shows that deep models are extremely vulnerable to backdoor attacks. The existing backdoor attacks mainly…

The security issue of large language models (LLMs) has gained wide attention recently, with various defense mechanisms developed to prevent harmful output, among which safeguards based on text embedding models serve as a fundamental…

This paper addresses the critical challenge of deriving interpretable confidence scores from generative language models (LLMs) when applied to multi-label content safety classification. While models like LLaMA Guard are effective for…

The opacity in developing large language models (LLMs) is raising growing concerns about the potential contamination of public benchmarks in the pre-training data. Existing contamination detection methods are typically based on the text…

Neural machine translation with millions of parameters is vulnerable to unfamiliar inputs. We propose Token Drop to improve generalization and avoid overfitting for the NMT model. Similar to word dropout, whereas we replace dropped token…

Textual adversarial attacks pose a serious security threat to Natural Language Processing (NLP) systems by introducing imperceptible perturbations that mislead deep learning models. While adversarial example detection offers a lightweight…

Adversarial misuse, particularly through `jailbreaking' that circumvents a model's safety and ethical protocols, poses a significant challenge for Large Language Models (LLMs). This paper delves into the mechanisms behind such successful…

Neural ranking models (NRMs) have undergone significant development and have become integral components of information retrieval (IR) systems. Unfortunately, recent research has unveiled the vulnerability of NRMs to adversarial document…

Jailbreaks are adversarial attacks designed to bypass the built-in safety mechanisms of large language models. Automated jailbreaks typically optimize an adversarial suffix or adapt long prompt templates by forcing the model to generate the…

Large Language Model (LLM) watermarking embeds detectable signals into generated text for copyright protection, misuse prevention, and content detection. While prior studies evaluate robustness using watermark removal attacks, these methods…