Related papers: A Data-Centric Approach for Safe and Secure Large …

Large Language Models (LLMs) remain vulnerable to jailbreak attacks that bypass their safety mechanisms. Existing attack methods are fixed or specifically tailored for certain models and cannot flexibly adjust attack strength, which is…

Large language models (LLMs) have exploded in popularity due to their ability to perform a wide array of natural language tasks. Text-based content moderation is one LLM use case that has received recent enthusiasm, however, there is little…

Data filtering strategies are a crucial component to develop safe Large Language Models (LLM), since they support the removal of harmful contents from pretraining datasets. There is a lack of research on the actual impact of these…

Large Language Models (LLMs) are typically aligned for safety during the post-training phase; however, they may still generate inappropriate outputs that could potentially pose risks to users. This challenge underscores the need for robust…

Large Language Models (LLMs) are transforming the robotics domain by enabling robots to comprehend and execute natural language instructions. The cornerstone benefits of LLM include processing textual data from technical manuals,…

Large Language Models (LLMs) represent a major step toward artificial general intelligence, significantly advancing our ability to interact with technology. While LLMs perform well on Natural Language Processing tasks -- such as…

Generative large language models (LLMs) have achieved state-of-the-art results on a wide range of tasks, yet they remain susceptible to backdoor attacks: carefully crafted triggers in the input can manipulate the model to produce…

Large language models (LLMs) frequently generate toxic content, posing significant risks for safe deployment. Current mitigation strategies often degrade generation quality or require costly human annotation. We propose CAUSALDETOX, a…

Hate speech has become pervasive in today's digital age. Although there has been considerable research to detect hate speech or generate counter speech to combat hateful views, these approaches still cannot completely eliminate the…

Multimodal large language models (MLLMs) excel in vision-language tasks but also pose significant risks of generating harmful content, particularly through jailbreak attacks. Jailbreak attacks refer to intentional manipulations that bypass…

Large reasoning models (LRMs) achieved remarkable performance via chain-of-thought (CoT), but recent studies showed that such enhanced reasoning capabilities are at the expense of significantly degraded safety capabilities. In this paper,…

Despite careful safety alignment, current large language models (LLMs) remain vulnerable to various attacks. To further unveil the safety risks of LLMs, we introduce a Safety Concept Activation Vector (SCAV) framework, which effectively…

The rapid advancement of Large Language Models (LLMs) in the realm of mathematical reasoning necessitates comprehensive evaluations to gauge progress and inspire future directions. Existing assessments predominantly focus on problem-solving…

With the development of natural language processing (NLP), large language models (LLMs) are becoming increasingly popular. LLMs are integrating more into everyday life, raising public concerns about their security vulnerabilities.…

Large Language Models (LLMs) are known to be susceptible to crafted adversarial attacks or jailbreaks that lead to the generation of objectionable content despite being aligned to human preferences using safety fine-tuning methods. While…

The safety alignment of large language models (LLMs) is becoming increasingly important with their democratization. In this paper, we study the safety degradation that comes with adapting LLMs to new tasks. We attribute this safety…

The recent release of very large language models such as PaLM and GPT-4 has made an unprecedented impact in the popular media and public consciousness, giving rise to a mixture of excitement and fear as to their capabilities and potential…

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…

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…

Machine Translation (MT) plays a pivotal role in cross-lingual information access, public policy communication, and equitable knowledge dissemination. However, critical meaning errors, such as factual distortions, intent reversals, or…