Impact

Safety Vulnerabilities

Security concerns affecting AI safety and alignment

6 matching entries out of 781 in this category

Safety research results

6 entries

Progressive Attention LVLM Attack

Updated 2/22/2026

Large Vision-Language Models (LVLMs) are vulnerable to a Stage-wise Attention-Guided Attack (SAGA) that allows for the generation of highly transferable, imperceptible adversarial examples. The vulnerability stems from a positive correlation between regional cross-modal attention scores and adversarial loss sensitivity in LVLMs. An attacker can exploit this by extracting an attention map from a surrogate open-source model (e.g., Qwen3-VL) to identify high-attention "hotspots." SAGA utilizes a…

Stage-wise Attention-Guided Region Sequencing for Adversarial Attacks on Large Vision-Language Models

Affects: Gemini 2.5 Flash, Gemini 3 Pro Preview, GPT-4.1 +7 more

Source: arXiv

Semantic Hierarchical VLM Transfer

Updated 2/22/2026

Large Vision-Language Models (VLMs) are vulnerable to a transferable targeted adversarial attack known as SGHA-Attack (Semantic-Guided Hierarchical Alignment). This vulnerability arises from the susceptibility of visual encoders (specifically Vision Transformers) to intermediate-layer feature manipulation optimized on a surrogate model (e.g., CLIP). An attacker can craft adversarial images by injecting imperceptible perturbations that enforce semantic consistency with a target text prompt…

SGHA-Attack: Semantic-Guided Hierarchical Alignment for Transferable Targeted Attacks on Vision-Language Models

Affects: UniDiffuser, BLIP-2 ViT-g/14, InstructBLIP Vicuna 13B +4 more

Source: arXiv

Special Token Jailbreak

Updated 10/31/2025

Large Language Models (LLMs) that use special tokens to define conversational structure (e.g., via chat templates) are vulnerable to a jailbreak attack named MetaBreak. An attacker can inject these special tokens, or regular tokens with high semantic similarity in the embedding space, into a user prompt. This manipulation allows the attacker to bypass the model's internal safety alignment and external content moderation systems. The attack leverages four primitives: 1. Response Injection…

MetaBreak: Jailbreaking Online LLM Services via Special Token Manipulation

Affects: Claude Opus 4, Gemma 2 27B IT, GPT-4.1 +9 more

Source: arXiv

Logit Leakage Model Clone

Updated 12/9/2025

Large Language Model (LLM) inference APIs that expose top-k logits or log-probabilities are vulnerable to model extraction and cloning. An attacker can execute a two-stage attack to replicate the proprietary model without access to weights, gradients, or training data. First, by submitting fewer than 10,000 random queries and aggregating the returned unrounded logits, the attacker recovers the model's output projection matrix using Singular Value Decomposition (SVD). Second, the attacker…

Clone What You Can't Steal: Black-Box LLM Replication via Logit Leakage and Distillation

Affects: GPT-3.5, Mistral 7B

Source: arXiv

Single Query Dynamic Output

Updated 12/9/2025

A vulnerability exists in Large Language Models (LLMs) and multi-label text classification systems that allows for Textual Dynamic Outputs Attacks (TDOA). This technique enables hard-label black-box attacks against systems with variable or generative output spaces (where the number of labels or specific label tokens are not fixed). The attack functions by training a surrogate model on clustered coarse-grained labels derived from the victim model's fine-grained dynamic outputs. It subsequently…

Text Adversarial Attacks with Dynamic Outputs

Affects: GPT-4o, GPT-4o Mini, GPT-4.1 +5 more

Source: arXiv

Agent Action Hijacking

Updated 3/19/2025

A vulnerability in LLM-based agents, dubbed AI Agent Injection (AI²), allows attackers to hijack the agent's actions by manipulating the agent's memory retrieval mechanism. The attack involves two main steps: (1) Stealing action-aware knowledge from the agent's memory using crafted adversarial queries targeting the retriever module and (2) Generating Trojan prompts consisting of a Trojan string and hijacking instructions. The Trojan string is designed to manipulate the retriever into…

Towards Action Hijacking of Large Language Model-based Agent

Affects: Alpaca, BERT, GPT-3 +3 more

Source: arXiv

Related research categories