Related papers: When Backdoors Speak: Understanding LLM Backdoor A…
The self-rationalising capabilities of large language models (LLMs) have been explored in restricted settings, using task/specific data sets. However, current LLMs do not (only) rely on specifically annotated data; nonetheless, they…
Large language models (LLMs) are susceptible to a type of attack known as jailbreaking, which misleads LLMs to output harmful contents. Although there are diverse jailbreak attack strategies, there is no unified understanding on why some…
Large Language Models (LLMs) have demonstrated remarkable capabilities in generating coherent text but remain limited by the static nature of their training data. Retrieval Augmented Generation (RAG) addresses this issue by combining LLMs…
The prevalence and strong capability of large language models (LLMs) present significant safety and ethical risks if exploited by malicious users. To prevent the potentially deceptive usage of LLMs, recent works have proposed algorithms to…
Explainable machine learning holds great potential for analyzing and understanding learning-based systems. These methods can, however, be manipulated to present unfaithful explanations, giving rise to powerful and stealthy adversaries. In…
We find that language models have difficulties generating fallacious and deceptive reasoning. When asked to generate deceptive outputs, language models tend to leak honest counterparts but believe them to be false. Exploiting this…
The growing dependence on machine learning in real-world applications emphasizes the importance of understanding and ensuring its safety. Backdoor attacks pose a significant security risk due to their stealthy nature and potentially serious…
The proliferation of large language models (LLMs) has sparked widespread and general interest due to their strong language generation capabilities, offering great potential for both industry and research. While previous research delved into…
Deep neural networks are vulnerable to backdoor attacks, a type of adversarial attack that poisons the training data to manipulate the behavior of models trained on such data. Clean-label attacks are a more stealthy form of backdoor attacks…
Large language models (LLMs) undergo alignment training to avoid harmful behaviors, yet the resulting safeguards remain brittle: jailbreaks routinely bypass them, and fine-tuning on narrow domains can induce ``emergent misalignment'' that…
Large language models (LLMs) have gained human trust due to their capabilities and helpfulness. However, this in turn may allow LLMs to affect users' mindsets by manipulating language. It is termed as gaslighting, a psychological effect. In…
Multi-modal large language models (MLLMs) extend large language models (LLMs) to process multi-modal information, enabling them to generate responses to image-text inputs. MLLMs have been incorporated into diverse multi-modal applications,…
Despite their growing adoption across domains, large language model (LLM)-powered agents face significant security risks from backdoor attacks during training and fine-tuning. These compromised agents can subsequently be manipulated to…
Although many large language models (LLMs) have been trained to refuse harmful requests, they are still vulnerable to jailbreaking attacks which rewrite the original prompt to conceal its harmful intent. In this paper, we propose a new…
In the field of natural language processing, the prevalent approach involves fine-tuning pretrained language models (PLMs) using local samples. Recent research has exposed the susceptibility of PLMs to backdoor attacks, wherein the…
The rapid development of large language models (LLMs) has not only provided numerous opportunities but also presented significant challenges. This becomes particularly evident when LLMs inadvertently generate harmful or toxic content,…
Instruction-tuned LMs such as ChatGPT, FLAN, and InstructGPT are finetuned on datasets that contain user-submitted examples, e.g., FLAN aggregates numerous open-source datasets and OpenAI leverages examples submitted in the browser…
Large language models (LLMs) possess strong semantic understanding, driving significant progress in data mining applications. This is further enhanced by large reasoning models (LRMs), which provide explicit multi-step reasoning traces. On…
Large Language Models (LLMs) suffer from a range of vulnerabilities that allow malicious users to solicit undesirable responses through manipulation of the input text. These so-called jailbreak prompts are designed to trick the LLM into…
Vision Language Models (VLMs) have shown remarkable performance, but are also vulnerable to backdoor attacks whereby the adversary can manipulate the model's outputs through hidden triggers. Prior attacks primarily rely on single-modality…