Skip to main content
LLM Security Database
Skip to research search
Last analyzed Sep 9, 2026

Language Model Security Database

985 research findings · 1119 evaluated models

Filtered research findings

468 entries

Matches every word across titles, descriptions, sources, affected systems, and models.

Black-Box Vision-Language Jailbreak

Published Analyzed Source: arXiv

Large Vision-Language Models (LVLMs), specifically InstructBLIP, LLaVA, and MiniGPT-4, are susceptible to a black-box adversarial jailbreak vulnerability via Zeroth-Order Simultaneous Perturbation Stochastic Approximation (ZO-SPSA). An attacker can generate adversarial images with imperceptible perturbations that, when paired with harmful text prompts, bypass the model's safety alignment mechanisms (such as RLHF). Unlike traditional white-box attacks, this method does not require access to…

Crafting Adversarial Inputs for Large Vision-Language Models Using Black-Box Optimization
Evaluated models: Llama 2 13B, InstructBLIP, Vicuna 13B

Aggressive Compression Model Theft

Published Analyzed Source: arXiv

Large Language Models (LLMs) hosted on inference servers are vulnerable to high-speed weight exfiltration attacks due to the inherent compressibility of transformer parameters when decompression constraints are relaxed. Adversaries with compromised server access can utilize aggressive lossy compression techniques—specifically additive quantization combined with k-means clustering—to reduce model size by factors of 16x to 100x (e.g., <1 bit per parameter). Unlike standard quantization for…

Aggressive Compression Enables LLM Weight Theft
Evaluated models: Qwen 2 1.5B, Qwen 2 7B, Qwen 2.5 0.5B+2 more
  • Qwen 2 1.5B
  • Qwen 2 7B
  • Qwen 2.5 0.5B
  • Qwen 2.5 1.5B
  • Pythia 70M

Direct Emoji Jailbreak

Published Analyzed Source: arXiv

Large Language Models (LLMs), specifically Mistral 7B, Gemma 2 9B, and Llama 3 8B, are vulnerable to safety filter bypass via "Emoji-Based Jailbreaking." This adversarial prompt engineering technique exploits the model's tokenization and internal representation of Unicode emoji characters. By utilizing "emoji stuffing" (inserting emojis between textual tokens) or "emoji chaining" (using sequences of emojis as semantic proxies for sensitive terms), attackers can evade keyword-based safety…

Emoji-Based Jailbreaking of Large Language Models
Evaluated models: Llama 3 8B, Mistral 7B, Qwen 2 7B+1 more
  • Llama 3 8B
  • Mistral 7B
  • Qwen 2 7B
  • Gemma 2 9B

LoRA Unverified Product Poisoning

Published Analyzed Source: arXiv

In distributed Low-Rank Adaptation (LoRA) fine-tuning systems, a structural verification blind spot exists due to the decoupled aggregation of low-rank matrices. Frameworks typically evaluate and aggregate the $A$ and $B$ matrices independently to reduce computational overhead. A malicious client can exploit this by submitting individually benign $A$ and $B$ matrices that satisfy standard norm-based and similarity-based anomaly detection filters, but whose composite product ($A \times B$)…

Low Rank Comes with Low Security: Gradient Assembly Poisoning Attacks against Distributed LoRA-based LLM Systems
Evaluated models: ChatGLM2 6B, GPT-2 124M, Llama 7B+2 more
  • ChatGLM2 6B
  • GPT-2 124M
  • Llama 7B
  • Llama 13B
  • Llama 33B

LLM Anthropomorphic Vulnerabilities

Published Analyzed Source: arXiv

Large Language Models (LLMs) deployed as autonomous agents exhibit "Anthropomorphic Vulnerability Inheritance" (AVI), a vulnerability class where models internalize human psychological failure modes during training. Attackers can bypass security controls and manipulate agent decision-making by exploiting semantic patterns associated with authority bias, artificial urgency, and social proof. Unlike traditional prompt injection which attempts to override system instructions, AVI exploits the…

The Silicon Psyche: Anthropomorphic Vulnerabilities in Large Language Models
Evaluated models: Claude Opus 4.5, Claude Sonnet 4.5, Claude Haiku 4.5+17 more
  • Claude Opus 4.5
  • Claude Sonnet 4.5
  • Claude Haiku 4.5
  • GPT-5.2 Pro
  • GPT-5.2 Thinking
  • o3-preview
  • o3-mini
  • Gemini 3 Pro
  • Gemini 3 Flash
  • Gemini 3 Deep Think
  • Llama 4 Scout
  • Llama 4 Maverick
  • Llama 3.3 70B
  • Mistral Large 3
  • Ministral 3
  • Devstral 2
  • DeepSeek V3.2
  • DeepSeek V3.2 Speciale
  • DeepSeek R1
  • Grok 4.1

LLM Psychological Jailbreak

Published Analyzed Source: arXiv

Instruction-tuned Large Language Models (LLMs) employing Reinforcement Learning from Human Feedback (RLHF) contain a behavioral vulnerability arising from "over-optimized social priors." This vulnerability, termed Psychological Jailbreak, allows attackers to bypass safety guardrails by exploiting the model’s optimization for anthropomorphic consistency. By establishing a Structured Persona Context (SPC) that aligns with latent psychometric traits (e.g., high agreeableness or neuroticism), an…

Breaking Minds, Breaking Systems: Jailbreaking Large Language Models via Human-like Psychological Manipulation
Evaluated models: GPT-3.5 Turbo, GPT-4o Mini, Gemini 2.0 Flash+2 more
  • GPT-3.5 Turbo
  • GPT-4o Mini
  • Gemini 2.0 Flash
  • Qwen 3 32B Instruct
  • DeepSeek V3

Adversarial Vision Degrades VLM

Published Analyzed Source: arXiv

Large Language and Vision Assistant (LLaVA) v1.5-13B and Meta Llama 3.2 11B Vision are vulnerable to adversarial evasion attacks targeting the visual input modality. An attacker with white-box access (knowledge of model architecture and gradients) can employ Projected Gradient Descent (PGD) to generate adversarial perturbations constrained by an L-infinity norm. By maximizing the model's internal loss function with respect to the input image, the attacker can force the Vision-Language Model…

Adversarial Robustness of Vision in Open Foundation Models
Evaluated models: LLaVA 1.5 13B, Llama 3.2 11B Vision

Abliteration Cripples Math

Published Analyzed Source: arXiv

Open-weight Large Language Models (LLMs) are vulnerable to a white-box safety alignment bypass known as "abliteration" (directional orthogonalization). An attacker with access to the model weights can compute the "refusal direction" in the residual stream activation space by contrasting internal activations between harmful and harmless prompts. By projecting the model's weight matrices to be orthogonal to this single direction (or specific concept cones), the safety alignment is surgically…

Comparative Analysis of LLM Abliteration Methods: A Cross-Architecture Evaluation
Evaluated models: Llama 3.1 8B Instruct, Mistral 7B Instruct v0.3, Qwen 2.5 7B Instruct+13 more
  • Llama 3.1 8B Instruct
  • Mistral 7B Instruct v0.3
  • Qwen 2.5 7B Instruct
  • Qwen 3 8B
  • Qwen 3 14B
  • Yi 1.5 9B Chat
  • Zephyr 7B Beta
  • DeepSeek LLM 7B Chat
  • StableLM 2 12B Chat
  • Gemma 2 9B IT
  • Gemma 7B IT
  • InternLM 2.5 7B Chat
  • OpenChat 3.5 0106
  • Phi 3 Small 8k Instruct
  • Vicuna 7B v1.5
  • Falcon-Mamba 7B Instruct

Pretrained Leak Jailbreak

Published Analyzed Source: arXiv

Large Language Models (LLMs) finetuned from open-weight pretrained sources inherit adversarial vulnerabilities encoded in the pretrained model's internal representations. An attacker with white-box access to a pretrained model (e.g., Llama-2, Llama-3) can identify linearly separable features in the hidden states that correlate with "transferable" jailbreak prompts. By exploiting these features using a Probe-Guided Projection (PGP) attack, the attacker can optimize adversarial suffixes on the…

One Leak Away: How Pretrained Model Exposure Amplifies Jailbreak Risks in Finetuned LLMs
Evaluated models: Llama 2 7B Chat, Llama 3 8B Instruct, DeepSeek LLM 7B Chat+5 more
  • Llama 2 7B Chat
  • Llama 3 8B Instruct
  • DeepSeek LLM 7B Chat
  • Gemma 7B IT
  • Llama 2 13B
  • Qwen 7B
  • Vicuna 7B v1.5
  • Mistral 7B Instruct v0.2

Frontier Multi-Turn Jailbreak

Published Analyzed Source: arXiv

Frontier Large Language Models (LLMs) exhibit a critical vulnerability to automated, adaptive multi-turn adversarial attacks, specifically those utilizing tree-based exploration algorithms (e.g., the TEMPEST framework). Unlike single-turn jailbreaks, this vulnerability exploits the model's inability to maintain safety alignment across extended conversation trajectories. An attacker using an automated agent can dynamically select from multiple adversarial strategies—such as academic framing…

Replicating TEMPEST at Scale: Multi-Turn Adversarial Attacks Against Trillion-Parameter Frontier Models
Evaluated models: Cogito 2.1, DeepSeek V3.1, Gemma 3 12B+7 more
  • Cogito 2.1
  • DeepSeek V3.1
  • Gemma 3 12B
  • GLM-4.6
  • GPT-oss 20B
  • GPT-oss 120B
  • Kimi K2
  • Kimi K2 Thinking
  • MiniMax M2
  • Mistral Large 3

Research methodology

Entries summarize publicly available primary-source security research. Model names reflect only systems explicitly evaluated by the cited paper, and measurements are research-reported unless independent verification is stated.

Discovery and publication are separate: new papers enter a candidate queue, then require human review and explicit approval before publication. Updates follow that review process, not a guaranteed daily publishing schedule. “Last analyzed” is the newest analysis date among published entries; it does not mean that all recent research has been covered.