Related papers: Attributional Safety Failures in Large Language Mo…
Alignment tuning has enabled large language models to excel in reasoning, instruction-following, and minimizing harmful generations. However, despite their widespread deployment, these models exhibit a monolingual bias, raising concerns…
Safety alignment in large language models (LLMs), particularly for cybersecurity tasks, primarily focuses on preventing misuse. While this approach reduces direct harm, it obscures a complementary failure mode: denial of assistance to…
Large language models (LLMs) undergo safety alignment to ensure safe conversations with humans. However, this paper introduces a training-free attack method capable of reversing safety alignment, converting the outcomes of stronger…
Most safety evaluations of large language models (LLMs) remain anchored in English. Translation is often used as a shortcut to probe multilingual behavior, but it rarely captures the full picture, especially when harmful intent or structure…
Guardrails are critical for the safe deployment of Large Language Models (LLMs)-powered software. Unlike traditional rule-based systems with limited, predefined input-output spaces that inherently constrain unsafe behavior, LLMs enable…
Code-switching (CSW) is the act of alternating between two or more languages within a single discourse. This phenomenon is widespread in multilingual communities, and increasingly prevalent in online content, where users naturally mix…
As large language models (LLMs) constantly evolve, ensuring their safety remains a critical research problem. Previous red-teaming approaches for LLM safety have primarily focused on single prompt attacks or goal hijacking. To the best of…
Large Language Models (LLMs) have emerged as powerful tools, but their inherent safety risks - ranging from harmful content generation to broader societal harms - pose significant challenges. These risks can be amplified by the recent…
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) demonstrate impressive capabilities across a wide range of tasks, yet their safety mechanisms remain susceptible to adversarial attacks that exploit cognitive biases -- systematic deviations from rational…
Multilingual Retrieval-Augmented Generation (RAG) enables large language models (LLMs) to perform knowledge-intensive tasks in multilingual settings by leveraging retrieved documents as external evidence. However, when the retrieved…
Fine-tuning a general-purpose large language model (LLM) for a specific domain or task has become a routine procedure for ordinary users. However, fine-tuning is known to remove the safety alignment features of the model, even when the…
Large language models (LLMs) have acquired the ability to handle longer context lengths and understand nuances in text, expanding their dialogue capabilities beyond a single utterance. A popular user-facing application of LLMs is the…
To address the trade-off between robustness and performance for robust VLM, we observe that function words could incur vulnerability of VLMs against cross-modal adversarial attacks, and propose Function-word De-Attention (FDA) accordingly…
The rapid adoption of Large Language Models(LLMs) for code generation has transformed software development, yet little attention has been given to how security vulnerabilities evolve through iterative LLM feedback. This paper analyzes…
We have uncovered a powerful jailbreak technique that leverages large language models' ability to diverge from prior context, enabling them to bypass safety constraints and generate harmful outputs. By simply instructing the LLM to deviate…
Large Language Models (LLMs) exhibit strong but shallow alignment: they directly refuse harmful queries when a refusal is expected at the very start of an assistant turn, yet this protection collapses once a harmful continuation is underway…
Large Language Models (LLMs) transform artificial intelligence, driving advancements in natural language understanding, text generation, and autonomous systems. The increasing complexity of their development and deployment introduces…
With the increasing adoption of large language models (LLMs), ensuring the safety of LLM systems has become a pressing concern. External LLM-based guardrail models have emerged as a popular solution to screen unsafe inputs and outputs, but…
Large language models exhibit systematic vulnerabilities to adversarial attacks despite extensive safety alignment. We provide a mechanistic analysis revealing that position-dependent gradient weakening during autoregressive training…