Related papers: Stochastic Monkeys at Play: Random Augmentations C…
Large language models (LLMs) excel in diverse applications but face dual challenges: generating harmful content under jailbreak attacks and over-refusal of benign queries due to rigid safety mechanisms. These issues are further complicated…
Backdoor attacks on large language models (LLMs) typically couple a secret trigger to an explicit malicious output. We show that this explicit association is unnecessary for common LLMs. We introduce a compliance-only backdoor: supervised…
This study systematically analyzes the vulnerability of 36 large language models (LLMs) to various prompt injection attacks, a technique that leverages carefully crafted prompts to elicit malicious LLM behavior. Across 144 prompt injection…
As LLMs develop increasingly advanced capabilities, there is an increased need to minimize the harm that could be caused to society by certain model outputs; hence, most LLMs have safety guardrails added, for example via fine-tuning. In…
Large language models (LLMs) remain vulnerable to jailbreak prompts that elicit harmful or policy-violating outputs, while many existing defenses rely on expensive fine-tuning, intrusive prompt rewriting, or external guardrails that add…
Fine-tuning language models is commonly believed to inevitably harm their safety, i.e., refusing to respond to harmful user requests, even when using harmless datasets, thus requiring additional safety measures. We challenge this belief…
Large Language Models (LLMs) have showcased remarkable capabilities across various domains. Accompanying the evolving capabilities and expanding deployment scenarios of LLMs, their deployment challenges escalate due to their sheer scale and…
Large Language Models (LLMs) suffer from a range of vulnerabilities that allow malicious users to solicit undesirable responses through manipulation of the input text. These so-called jailbreak prompts are designed to trick the LLM into…
Safety alignment is a key requirement for building reliable Artificial General Intelligence. Despite significant advances in safety alignment, we observe that minor latent shifts can still trigger unsafe responses in aligned models. We…
Large Language Models (LLMs) face threats from jailbreak prompts. Existing methods for defending against jailbreak attacks are primarily based on auxiliary models. These strategies, however, often require extensive data collection or…
Safety alignment of large language models (LLMs) has been gaining increasing attention. However, current safety-aligned LLMs suffer from the fragile and imbalanced safety mechanisms, which can still be induced to generate unsafe responses,…
Evaluating the value alignment of large language models (LLMs) has traditionally relied on single-sentence adversarial prompts, which directly probe models with ethically sensitive or controversial questions. However, with the rapid…
Recent explorations with commercial Large Language Models (LLMs) have shown that non-expert users can jailbreak LLMs by simply manipulating their prompts; resulting in degenerate output behavior, privacy and security breaches, offensive…
We identify a structural weakness in current large language model (LLM) alignment: modern refusal mechanisms are fail-open. While existing approaches encode refusal behaviors across multiple latent features, suppressing a single dominant…
While large language models (LLMs) such as Llama-2 or GPT-4 have shown impressive zero-shot performance, fine-tuning is still necessary to enhance their performance for customized datasets, domain-specific tasks, or other private needs.…
Large language models (LLMs) can be prompted with specific styles (e.g., formatting responses as lists), including in malicious queries. Prior jailbreak research mainly augments these queries with additional string transformations 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) remain vulnerable to jailbreaking attacks where adversarial prompts elicit harmful outputs. Yet most evaluations focus on single-turn interactions while real-world attacks unfold through adaptive multi-turn…
When LLMs are deployed in sensitive, human-facing settings, it is crucial that they do not output unsafe, biased, or privacy-violating outputs. For this reason, models are both trained and instructed to refuse to answer unsafe prompts such…
Large Language Models(LLMs) have been successful in numerous fields. Alignment has usually been applied to prevent them from harmful purposes. However, aligned LLMs remain vulnerable to jailbreak attacks that deliberately mislead them into…