Language Model Security Database

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) are vulnerable to prompt injection attacks that can bypass their internal copyright compliance mechanisms, causing them to generate verbatim copyrighted text. The vulnerability stems from insufficient robustness against prompt engineering techniques that manipulate the model into ignoring or circumventing its safety filters designed for copyright protection.

Large Language Models (LLMs) used to control robots exhibit biases leading to discriminatory and unsafe behaviors. When provided with personal characteristics (e.g., race, gender, disability), LLMs generate biased outputs resulting in discriminatory actions (e.g., assigning lower rescue priority to certain groups) and accept or deem feasible dangerous or unlawful instructions (e.g., removing a person's mobility aid).

Large Language Models (LLMs) are vulnerable to prompt extraction attacks via inversion of their normal outputs. An attacker can train a model to reconstruct the prompt used to generate multiple outputs from an LLM, even without access to internal model parameters (logits) or requiring adversarial queries. This allows extraction of both user and system prompts.

Large language models (LLMs) are vulnerable to jailbreaking attacks using adversarially generated suffixes. The AmpleGCG attack generates a large number of diverse, effective suffixes which bypass safety mechanisms in both open and closed-source LLMs. The attack leverages the observation that low loss during suffix generation is not a reliable indicator of jailbreaking success, and generates diverse suffixes from intermediate steps of the optimization process.

A color-aware attack, Self Color Testing-based Substitution (SCTS), bypasses watermarking mechanisms in LLMs designed to identify AI-generated text. SCTS exploits the LLM's compliance with instructions to infer the "color" (green/red token classification) of tokens, allowing for targeted substitution of watermarked tokens with non-watermarked tokens, thus evading watermark detection. The attack is particularly effective against watermarks that utilize logit perturbation to bias token selection.

Large Language Models (LLMs) are vulnerable to black-box identity verification attacks using Targeted Random Adversarial Prompts (TRAP). TRAP leverages adversarial suffixes to elicit a pre-defined response from a target LLM, while other models produce random outputs, enabling identification of the specific LLM used within a third-party application via black-box access. This allows unauthorized identification of the underlying LLM even without access to model weights or internal parameters.

Large Language Models (LLMs) such as Llama 2 and Vicuna exhibit a vulnerability where specific layers (e.g., layer 3 in Llama2-13B, layer 1 in Llama2-7B and Vicuna-13B) overfit to harmful prompts, resulting in a disproportionate influence on the model's output for such prompts. This overfitting creates a narrow "safety" mechanism easily bypassed by adversarial prompts designed to avoid triggering these specific layers. Additionally, a single neuron (e.g., neuron 2100 in Llama2 and Vicuna)…

Large Language Models (LLMs) with accessible output logits are vulnerable to "coercive interrogation," a novel attack that extracts harmful knowledge hidden in low-ranked tokens. The attack doesn't require crafted prompts; instead, it iteratively forces the LLM to select and output low-probability tokens at key positions in the response sequence, revealing toxic content the model would otherwise suppress.

A prompt injection vulnerability in OpenAI's custom GPT models allows attackers to extract the system prompt and potentially leak user-uploaded files. Attackers craft malicious prompts that manipulate the LLM into revealing sensitive information, even when defensive prompts are in place. The vulnerability is exacerbated when the model includes a code interpreter.