Language Model Security Database

A vulnerability in large language models (LLMs) allows attackers to craft malicious prompts that induce the LLM to generate harmful content, such as fraudulent material, racist remarks, or instructions for illegal activities. The vulnerability arises from the LLM's inability to reliably distinguish between benign and malicious instructions disguised within seemingly innocuous prompts. Attackers can exploit this by leveraging techniques like obfuscation, code injection/payload splitting, and…

Large Language Models (LLMs), such as GPT-4, exhibit a cross-lingual vulnerability in their safety mechanisms. Translating unsafe English prompts into low-resource languages, using readily available translation APIs like Google Translate, bypasses the LLM's safety filters and elicits harmful responses with a significantly higher success rate than attacks targeting the English language directly. The vulnerability stems from an unequal distribution of safety training data across languages…

A prompt-based adversarial attack, termed PromptAttack, can cause Large Language Models (LLMs) to generate incorrect outputs by manipulating the input prompt. PromptAttack crafts prompts that include the original input, an attack objective (to generate semantically similar but misclassified output), and attack guidance with instructions for character, word, or sentence-level perturbations. This allows an attacker to manipulate an LLM's response without direct access to its internal parameters…

Large Language Models (LLMs) are susceptible to automated jailbreak attacks using a fuzzing framework that generates variations of existing jailbreak prompts. This vulnerability allows bypassing built-in safety mechanisms, leading to the generation of harmful or unintended outputs. The vulnerability stems from the LLMs' inability to consistently recognize and reject semantically similar, but subtly different prompt variations generated through automated mutation techniques.

A universal black-box jailbreaking vulnerability exists in Large Language Models (LLMs) due to their susceptibility to adversarial prompts crafted using a genetic algorithm (GA). The GA optimizes a universal adversarial prompt suffix that, when appended to various user inputs, causes the LLM to generate unintended and potentially harmful outputs, bypassing safety mechanisms. This attack requires no knowledge of the LLM's internal architecture or parameters.

Large Language Models (LLMs) are vulnerable to a "Chain of Utterances" (CoU) based prompt injection attack. This attack exploits the LLM's ability to engage in multi-turn conversations and role-playing, tricking it into providing harmful or unsafe responses even when presented with safety guidelines. The attack leverages a crafted conversation between two agents ("Red-LM," a malicious agent, and "Base-LM," a seemingly helpful agent) to elicit unethical responses from the Base-LM by subtly…

Large Language Models (LLMs) such as GPT-4, while employing safety alignment techniques, exhibit vulnerability to "CipherChat" attacks. CipherChat leverages cipher prompts (e.g., ASCII, Unicode, Caesar cipher, Morse code) combined with system role descriptions and few-shot enciphered demonstrations to bypass safety mechanisms trained on natural language. This allows an attacker to elicit unsafe responses from the LLM, effectively evading safety filters. The vulnerability is amplified by the…

The MASTER KEY framework exploits timing-based characteristics of Large Language Model (LLM) chatbot responses to infer internal defense mechanisms and automatically generate jailbreak prompts. This allows bypassing safety restrictions and eliciting responses violating usage policies, including generation of illegal, harmful, privacy-violating, and adult content. The framework utilizes a three-step process: reverse-engineering defenses via time-based analysis, creating proof-of-concept…

A vulnerability in multi-modal large language models (LLMs) allows adversaries to bypass safety mechanisms through compositional adversarial attacks. The attack leverages the alignment between vision and language encoders, injecting malicious triggers into benign-looking images. These images, when paired with innocuous prompts, cause the LLM to generate harmful content. The attack requires access only to the vision encoder (e.g., CLIP), not the LLM itself, lowering the barrier to attack.

Aligned large language models (LLMs) are vulnerable to a universal and transferable adversarial suffix attack. Appending a specific, automatically generated suffix to a wide range of prompts, even those requesting objectionable content, causes the models to generate harmful or objectionable responses instead of refusing the request. The attack's success rate is significantly higher on GPT-based models.