Language Model Security Database

A training-time attack against open-source LLMs that injects adversarial embeddings into the model's token embeddings without modifying model weights. This allows an attacker to introduce backdoors, jailbreaks, or prompt stealing capabilities by simply modifying specific token embeddings within the model file, maintaining model utility for non-triggered inputs. The attack leverages soft prompt tuning to optimize adversarial embeddings, which are then assigned to chosen trigger tokens.

Appending a single whitespace character (space) or certain punctuation marks to the end of an LLM's input template can bypass safety mechanisms and cause the model to generate unsafe, biased, or factually incorrect outputs, even if the original prompt was benign. This vulnerability is due to the statistical properties of single-character tokens in the model's training data, causing unintended behavior in the model's token prediction.

Large language models (LLMs) employing safety measures like filters and alignment training remain vulnerable to information leakage via "Decomposition Attacks". These attacks decompose a malicious query into multiple benign sub-queries, eliciting responses from the LLM that, when aggregated, reveal sensitive information without triggering safety filters or producing directly harmful outputs.

Large Language Models (LLMs), specifically Llama 3 8B and 70B, are vulnerable to a rapid removal of safety fine-tuning through parameter-efficient fine-tuning (PEFT) methods. Attackers with access to model weights can use techniques like QLoRA, ReLoRA, or Ortho to effectively circumvent safety mechanisms in a matter of minutes using readily available computational resources. This allows bypassing safety restrictions and eliciting unsafe outputs.

Large Language Models (LLMs) struggle to generate genuinely fallacious reasoning. When prompted to create a false procedure for a harmful task, the LLMs instead leak the correct, harmful procedure while incorrectly claiming it's false. This vulnerability allows bypassing safety mechanisms and eliciting harmful outputs.

A vulnerability in LLM finetuning APIs allows covert malicious finetuning. Attackers can create a dataset where individual data points appear innocuous but, when used for finetuning, teach the LLM to respond to encoded harmful requests with encoded harmful responses. This bypasses existing safety checks and evaluations because the training data appears benign.

Large language models (LLMs) are vulnerable to jailbreak attacks that leverage the injection of special tokens to manipulate the model's interpretation of user input. By strategically inserting special tokens (e.g., <SEP>) that delineate user input and model output, attackers can trick the LLM into treating part of the user-provided input as its own generated content, thereby bypassing safety mechanisms and eliciting harmful responses. This allows attackers to increase the success rate of…

A vulnerability in Retrieval-Augmented Generation (RAG) systems utilizing LangChain allows for indirect jailbreaks of Large Language Models (LLMs). By poisoning the external knowledge base accessed by the LLM through LangChain, attackers can manipulate the LLM's responses, causing it to generate malicious or inappropriate content. The attack exploits the LLM's reliance on the external knowledge base and bypasses direct prompt-based jailbreak defenses.

LLMs, even when individually assessed as "safe," can be combined by an adversary to achieve malicious outcomes. This vulnerability exploits the complementary strengths of multiple models—a high-capability model that refuses malicious requests and a low-capability model that does not—through task decomposition. Adversaries can either manually decompose tasks into benign (solved by the high-capability model) and easily-malicious subtasks (solved by the low-capability model) or automate the…

Large Language Models (LLMs) trained with reinforcement learning from human feedback (RLHF) are vulnerable to jailbreaking attacks due to reward misspecification. The reward function used during alignment fails to accurately rank the quality of responses, particularly for adversarial prompts designed to elicit undesired behavior. This allows attackers to craft prompts that yield harmful outputs despite the model's intended safety constraints. The vulnerability manifests as a gap between the…