Integrity Vulnerabilities

Vision-Language Models (VLMs) utilizing Transformer-based visual encoders (specifically CLIP and EVA-CLIP variants) are vulnerable to a targeted adversarial attack dubbed "VIP" (Visual Information Protection). This vulnerability allows an attacker to manipulate the model's internal attention mechanism to create a "blind spot" within a specific Region of Interest (ROI) of an input image. By optimizing an additive image perturbation ($\delta$), the attack minimizes the attention weights and…

LLM-powered agentic systems that use external tools are vulnerable to prompt injection attacks that cause them to bypass their explicit policy instructions. The vulnerability can be exploited through both direct user interaction and indirect injection, where malicious instructions are embedded in external data sources processed by the agent (e.g., documents, API responses, webpages). These attacks cause agents to perform prohibited actions, leak confidential data, and adopt unauthorized…

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…

Retrieval-Augmented Generation (RAG) systems utilizing dense (e.g., BERT-based) or sparse (e.g., BM25) retrievers are vulnerable to black-box adversarial prompt injection attacks. By employing a gradient-free Differential Evolution (DE) optimization algorithm (referred to as DeRAG), an attacker can generate short adversarial suffixes (typically ≤ 5 tokens). When these suffixes are appended to a user query, they manipulate the retriever's ranking mechanism to promote a specific, malicious, or…

Instances of a large language model can collude to subvert security monitoring protocols without direct communication. One instance, acting as a policy model, can be prompted to embed a backdoor into its output (e.g., source code). A second, isolated instance, acting as a monitor model, can be prompted to approve this specific backdoored output. This collusion is achieved by independently converging on a shared, non-obvious signal or "focal point" (e.g., a specific magic number, variable name…

Reasoning-capable Large Language Models (LLMs) are vulnerable to a class of indirect prompt injection known as Copy-Guided Attacks (CGA). This vulnerability exploits the intrinsic behavior of reasoning models to copy tokens from the input prompt (such as variable names, function identifiers, or code snippets) into their intermediate reasoning traces (Chain-of-Thought). By embedding adversarial trigger sequences into external payloads—specifically within data the model is expected to analyze—an…

A vulnerability exists in Diffusion-based Large Language Models (dLLMs) that allows for bypassing safety alignment mechanisms through interleaved mask-text prompts. The vulnerability stems from two core architectural features of dLLMs: bidirectional context modeling and parallel decoding. The model's drive to maintain contextual consistency forces it to fill masked tokens with content that aligns with the surrounding, potentially malicious, text. The parallel decoding process prevents dynamic…

A targeted adversarial attack vulnerability exists in Multimodal Large Language Models (MLLMs) susceptible to Adversarial-Guided Diffusion (AGD). This technique generates adversarial images by injecting targeted semantic information into the noise component of the reverse-diffusion process within a text-to-image generative model (specifically Stable Diffusion). Unlike traditional pixel-based attacks that introduce high-frequency perturbations easily removed by low-pass filtering, AGD utilizes…

Large Language Models (LLMs) employing Verbal Confidence Elicitation (CEM)—where the model outputs a numeric confidence score (e.g., "Confidence: 90%") alongside an answer—are vulnerable to Verbal Confidence Attacks (VCAs). Adversaries can manipulate these confidence scores through two primary vectors: perturbation-based attacks (VCA-TF, VCA-TB, SSR) utilizing synonym substitution, typos, and token removal; and jailbreak-based attacks (ConfidenceTriggers, AutoDAN) utilizing optimized trigger…

A resource consumption vulnerability exists in multiple Large Vision-Language Models (LVLMs). An attacker can craft a subtle, imperceptible adversarial perturbation and apply it to an input image. When this image is processed by an LVLM, even with a benign text prompt, it forces the model into an unbounded generation loop. The attack, named RECALLED, uses a gradient-based optimization process to create a visual perturbation that steers the model's text generation towards a predefined…