Related papers: Virus: Harmful Fine-tuning Attack for Large Langua…
This research article critically examines the potential risks and implications arising from the malicious utilization of large language models(LLM), focusing specifically on ChatGPT and Google's Bard. Although these large language models…
The AI era has ushered in Large Language Models (LLM) to the technological forefront, which has been much of the talk in 2023, and is likely to remain as such for many years to come. LLMs are the AI models that are the power house behind…
Multimodal large language models (MLLMs) are gaining increasing attention. Due to the heterogeneity of their input features, they face significant challenges in terms of jailbreak defenses. Current defense methods rely on costly fine-tuning…
This paper introduces MetaDefense, a novel framework for defending against finetuning-based jailbreak attacks in large language models (LLMs). We observe that existing defense mechanisms fail to generalize to harmful queries disguised by…
As powerful Large Language Models (LLMs) are now widely used for numerous practical applications, their safety is of critical importance. While alignment techniques have significantly improved overall safety, LLMs remain vulnerable to…
Safety guardrails in large language models(LLMs) are developed to prevent malicious users from generating toxic content at a large scale. However, these measures can inadvertently introduce or reflect new biases, as LLMs may refuse to…
Large language models (LLMs) employ safety mechanisms to prevent harmful outputs, yet these defenses primarily rely on semantic pattern matching. We show that encoding harmful prompts as coherent mathematical problems -- using formalisms…
Large Language Models (LLMs) exhibit impressive capabilities but also present risks such as biased content generation and privacy issues. One of the current alignment techniques includes principle-driven integration, but it faces challenges…
Accurate rejection of sensitive or harmful visual content, i.e., harmful image guardrail, is critical in many application scenarios. This task must continuously adapt to the evolving safety policies and content across various domains and…
This paper explores the pressing issue of risk assessment in Large Language Models (LLMs) as they become increasingly prevalent in various applications. Focusing on how reward models, which are designed to fine-tune pretrained LLMs to align…
Large Language Models (LLMs) have transformed artificial intelligence by advancing natural language understanding and generation, enabling applications across fields beyond healthcare, software engineering, and conversational systems.…
Large Language Models (LLMs) have achieved remarkable progress, but their deployment has exposed critical vulnerabilities, particularly to jailbreak attacks that circumvent safety alignments. Guardrails--external defense mechanisms that…
Guardrail models (a.k.a. safety checkers) are widely deployed to screen user inputs before they reach large language models (LLMs), serving as a primary defense against prompt injection attacks. Due to strict context constraints, these…
Large Language Models (LLMs) are powerful tools for answering user queries, yet they remain highly vulnerable to jailbreak attacks. Existing guardrail methods typically rely on internal features or textual responses to detect malicious…
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…
The rapid advancement of Large Vision-Language Models (LVLMs) is increasingly accompanied by unauthorized scraping and training on multimodal web data, posing severe copyright and privacy risks to data owners. Existing countermeasures, such…
Fine-tuning Large Language Models (LLMs) on benign narrow data can sometimes induce broad harmful behaviors, a vulnerability termed emergent misalignment (EM). While prior work links these failures to specific directions in the activation…
With the significant development of large models in recent years, Large Vision-Language Models (LVLMs) have demonstrated remarkable capabilities across a wide range of multimodal understanding and reasoning tasks. Compared to traditional…
Vision language models (VLMs) extend the reasoning capabilities of large language models (LLMs) to cross-modal settings, yet remain highly vulnerable to multimodal jailbreak attacks. Existing defenses predominantly rely on safety…
Black-box finetuning is an emerging interface for adapting state-of-the-art language models to user needs. However, such access may also let malicious actors undermine model safety. To demonstrate the challenge of defending finetuning…