Language Model Security Database

Audio-Language Models (ALMs) including Qwen2.5-Omni (3B and 7B) and Phi-4-Multimodal are vulnerable to "WhisperInject," a two-stage adversarial audio attack that bypasses safety guardrails. The vulnerability allows an attacker to inject imperceptible perturbations into benign audio inputs (e.g., a query about the weather) that force the model to generate specific harmful content. The attack utilizes a novel optimization method, Reinforcement Learning with Projected Gradient Descent (RL-PGD)…

A vulnerability exists in the fine-tuning lifecycle of Vision-Language Models (VLMs) derived from open-source base models, termed the "grey-box threat." Adversaries with white-box access to a public base model (e.g., Qwen2-VL) can generate universal adversarial images that successfully bypass safety guardrails in proprietary, fine-tuned downstream variants. This is achieved via the Simulated Ensemble Attack (SEA), which combines two techniques: Fine-tuning Trajectory Simulation (FTS), where…

Audio-based Large Language Models (ALLMs), specifically Qwen2-Audio, are vulnerable to over-the-air adversarial audio attacks. An attacker with white-box access can generate robust adversarial audio perturbations using gradient-based optimization combined with audio augmentation techniques (specifically SpecAugment, translation, and additive noise). These perturbations, when played through a speaker in the physical environment, manipulate the ALLM processing the audio via a microphone. This…

A vulnerability termed "Trojan Horse Prompting" exists in conversational multimodal models, specifically demonstrated on Google’s Gemini-2.0-flash-preview-image-generation. The vulnerability allows an attacker to bypass safety alignment mechanisms (RLHF and SFT) by manipulating the structural protocol of the conversational API. Unlike standard jailbreaks that manipulate the user prompt, this attack exploits "Asymmetric Safety Alignment" by forging a conversational history where the role is…

Adversarial Activation Patching enables the induction of emergent deceptive behaviors in safety-aligned transformer-based Large Language Models (LLMs). By extracting intermediate activations ($A_{d}$) generated during the processing of a deceptive or harmful prompt and injecting them into the forward pass of a benign target prompt ($x_{t}$) at specific layers (specifically mid-layers, e.g., 5-10 in 32-layer architectures), an attacker can manipulate the model's internal reasoning circuits…

Large Language Models (LLMs) and Text-to-Image (T2I) models are vulnerable to jailbreaking through prompt-based attacks that use narrative framing, semantic substitution, and context diffusion to bypass safety moderation pipelines. These attacks do not require specialized knowledge or technical expertise. Attackers can embed harmful requests within benign narratives, frame them as fictional or professional inquiries, or use euphemistic language to circumvent input filters and output…

Multimodal Large Language Models (MLLMs) are vulnerable to visual contextual attacks, where carefully crafted images and accompanying text prompts can bypass safety mechanisms and elicit harmful responses. The vulnerability stems from the MLLM's ability to integrate visual and textual context to generate outputs, allowing attackers to create realistic scenarios that subvert safety filters. Specifically, the attack leverages image-driven context injection to construct deceptive multi-turn…

A vulnerability exists in the safety alignment mechanisms of Large Language Models (LLMs) (including GPT-4, Claude 3, Gemini, and Qwen families) leading to "Implicit Harm." Unlike traditional jailbreaks that use overtly harmful queries, this vulnerability allows remote attackers to coerce the model into providing factually incorrect, plausible, and dangerous responses to benign-looking inputs. By employing "JailFlip" techniques—specifically constructed affirmative-type or denial-type queries…

A vulnerability in SpeechGPT allows bypassing safety filters through adversarial audio prompts crafted by a white-box token-level attack. The attacker leverages knowledge of SpeechGPT's internal speech tokenization process to generate adversarial token sequences, which are then synthesized into audio. These audio prompts elicit restricted or harmful outputs the model would normally suppress. The attack's effectiveness relies on the model's discrete audio token representation and does not…

A vulnerability exists in multiple large language and multimodal models that allows for the bypass of safety filters through the use of code-mixed prompts with phonetic perturbations. An attacker can craft a prompt in a code-mixed language (e.g., Hinglish) and apply phonetic misspellings to sensitive keywords (e.g., spelling "hate" as "haet"). This technique causes the model's tokenizer to parse the sensitive word into benign sub-tokens, preventing safety mechanisms from flagging the harmful…