Related papers: Single Character Perturbations Break LLM Alignment
The focus on safety alignment in large language models (LLMs) has increased significantly due to their widespread adoption across different domains. The scale of LLMs play a contributing role in their success, and the growth in parameter…
Large Audio Language Models (LALMs) have extended the capabilities of Large Language Models (LLMs) by enabling audio-based human interactions. However, recent research has revealed that LALMs remain vulnerable to harmful queries due to…
This paper presents a systematic evaluation of Large Language Models' (LLMs) behavior on long-tail distributed (encrypted) texts and their safety implications. We introduce a two-dimensional framework for assessing LLM safety: (1)…
Large Language Models (LLMs) are regularly being used to label data across many domains and for myriad tasks. By simply asking the LLM for an answer, or ``prompting,'' practitioners are able to use LLMs to quickly get a response for an…
Recent research on large language models (LLMs) has demonstrated their ability to understand and employ deceptive behavior, even without explicit prompting. However, such behavior has only been observed in rare, specialized cases and has…
Large Language Models (LLMs), which bridge the gap between human language understanding and complex problem-solving, achieve state-of-the-art performance on several NLP tasks, particularly in few-shot and zero-shot settings. Despite the…
While Large Language Models (LLMs) have shown significant advancements in performance, various jailbreak attacks have posed growing safety and ethical risks. Malicious users often exploit adversarial context to deceive LLMs, prompting them…
The rise of multimodal large language models has introduced innovative human-machine interaction paradigms but also significant challenges in machine learning safety. Audio-Language Models (ALMs) are especially relevant due to the intuitive…
While recent code-specific large language models (LLMs) have greatly enhanced their code generation capabilities, the safety of these models remains under-explored, posing potential risks as insecure code generated by these models may…
Public LLMs such as the Llama 2-Chat underwent alignment training and were considered safe. Recently Qi et al. [2024] reported that even benign fine-tuning on seemingly safe datasets can give rise to unsafe behaviors in the models. The…
Large-language-model coding tools are now mainstream in software engineering. But as these same tools move human effort up the development stack, they present fresh dangers: 10% of real prompts leak private data, 42% of generated snippets…
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…
Large language models are now tuned to align with the goals of their creators, namely to be "helpful and harmless." These models should respond helpfully to user questions, but refuse to answer requests that could cause harm. However,…
Recently, Large Language Models (LLMs) have made significant advancements and are now widely used across various domains. Unfortunately, there has been a rising concern that LLMs can be misused to generate harmful or malicious content.…
Instruction-tuned large language models produce helpful, structured responses, but how robust is this helpfulness under trivial constraints? We show that simple lexical constraints (banning a single punctuation character or common word)…
The growing awareness of safety concerns in large language models (LLMs) has sparked considerable interest in the evaluation of safety. This study investigates an under-explored issue about the evaluation of LLMs, namely the substantial…
As large language models (LLMs) continue to advance in capabilities, ensuring their safety against jailbreak attacks remains a critical challenge. In this paper, we introduce a novel safety alignment approach called Answer-Then-Check, which…
While multimodal large language models (MLLMs) have achieved remarkable success in recent advancements, their susceptibility to jailbreak attacks has come to light. In such attacks, adversaries exploit carefully crafted prompts to coerce…
Large Language Models (LLMs) are powerful tools with profound societal impacts, yet their ability to generate responses to diverse and uncontrolled inputs leaves them vulnerable to adversarial attacks. While existing defenses often struggle…
Large Language Models (LLMs) can acquire deceptive behaviors through backdoor attacks, where the model executes prohibited actions whenever secret triggers appear in the input. Existing safety training methods largely fail to address this…