Related papers: Same Model, Different Weakness: How Language and M…
While the widespread deployment of Large Language Models (LLMs) holds great potential for society, their vulnerabilities to adversarial manipulation and exploitation can pose serious safety, security, and ethical risks. As new threats…
Research endeavors have been made in learning robust Multimodal Large Language Models (MLLMs) against jailbreak attacks. However, existing methods for improving MLLMs' robustness still face critical challenges: \ding{172} how to efficiently…
Humanitarian organizations face a critical choice: invest in costly commercial APIs or rely on free open-weight models for multilingual human rights monitoring. While commercial systems offer reliability, open-weight alternatives lack…
The systems and software powered by Large Language Models (LLMs) and Multi-Modal LLMs (MLLMs) have played a critical role in numerous scenarios. However, current LLM systems are vulnerable to prompt-based attacks, with jailbreaking attacks…
This work aims to investigate how different Large Language Models (LLMs) alignment methods affect the models' responses to prompt attacks. We selected open source models based on the most common alignment methods, namely, Supervised…
With the ubiquity of Large Language Models (LLMs), guardrails have become crucial to detect and defend against toxic content. However, with the increasing pervasiveness of LLMs in multilingual scenarios, their effectiveness in handling…
Large Language Models (LLMs) have revolutionized artificial intelligence, demonstrating remarkable computational power and linguistic capabilities. However, these models are inherently prone to various biases stemming from their training…
As safety remains a crucial concern throughout the development lifecycle of Large Language Models (LLMs), researchers and industrial practitioners have increasingly focused on safeguarding and aligning LLM behaviors with human preferences…
Large language models (LLMs) remain vulnerable to sophisticated prompt engineering attacks that exploit contextual framing to bypass safety mechanisms, posing significant risks in cybersecurity applications. We introduce Jailbreak Mimicry,…
Refusal mechanisms in large language models (LLMs) are essential for ensuring safety. Recent research has revealed that refusal behavior can be mediated by a single direction in activation space, enabling targeted interventions to bypass…
Large language models (LLMs) are increasingly being adopted in a wide range of real-world applications. Despite their impressive performance, recent studies have shown that LLMs are vulnerable to deliberately crafted adversarial prompts…
In recent years, the rapid development of large language models (LLMs) has achieved remarkable performance across various tasks. However, research indicates that LLMs are vulnerable to jailbreak attacks, where adversaries can induce the…
Despite multilingual pretraining, large language models often struggle with non-English tasks, particularly in language control, the ability to respond in the intended language. We identify and characterize two key failure modes: the…
Large Audio Language Models (LALMs) expand jailbreak risks from token-level prompting to the full speech perception-to-reasoning pipeline, where unsafe behavior can be induced through semantics, acoustic style, signal artifacts, or internal…
This study identifies the potential vulnerabilities of Large Language Models (LLMs) to 'jailbreak' attacks, specifically focusing on the Arabic language and its various forms. While most research has concentrated on English-based prompt…
Jailbreaking attacks on large language models pose a significant threat to AI safety by enabling the generation of harmful or restricted content. While prior work has explored both handcrafted and automated jailbreak strategies, the…
The implications of backdoor attacks on English-centric large language models (LLMs) have been widely examined - such attacks can be achieved by embedding malicious behaviors during training and activated under specific conditions that…
The rapid adoption of Mixture-of-Experts (MoE) architectures marks a major shift in the deployment of Large Language Models (LLMs). MoE LLMs improve scaling efficiency by activating only a small subset of parameters per token, but their…
Large language models (LLMs) have revolutionized artificial intelligence, but their increasing deployment across critical domains has raised concerns about their abnormal behaviors when faced with malicious attacks. Such vulnerability…
Multimodal Large Language Models (MLLMs) have achieved remarkable success in cross-modal understanding and generation, yet their deployment is threatened by critical safety vulnerabilities. While prior works have demonstrated the…