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.

Low-Resource Language Toxicity

Published Analyzed Source: arXiv

Large Language Models (LLMs) exhibit a significantly lower safety threshold when prompted in low-resource languages, such as Singlish, Malay, and Tamil, compared to high-resource languages like English. This vulnerability allows for the generation of toxic, biased, and hateful content through simple prompts. The models are susceptible to "toxicity jailbreaks" where providing a few toxic examples in-context (few-shot prompting) causes a substantial increase in the generation of harmful outputs…

Toxicity Red-Teaming: Benchmarking LLM Safety in Singapore's Low-Resource Languages
Evaluated models: GPT-4o Mini, Llama 3.1 8B Instruct, Mistral 7B Instruct v0.3+3 more
  • GPT-4o Mini
  • Llama 3.1 8B Instruct
  • Mistral 7B Instruct v0.3
  • Qwen 2.5 7B Instruct
  • Sea-Lion v2 Instruct
  • SeaLLM v3 7B Chat

Helpfulness-Oriented Jailbreak via Learning

Published Analyzed Source: arXiv

A vulnerability exists in multiple Large Language Models (LLMs) where safety alignment mechanisms can be bypassed by reframing harmful instructions as "learning-style" or academic questions. This technique, named Hiding Intention by Learning from LLMs (HILL), transforms direct, harmful requests into exploratory questions using simple hypotheticality indicators (e.g., "for academic curiosity", "in the movie") and detail-oriented inquiries (e.g., "provide a step-by-step breakdown"). The attack…

A Simple and Efficient Jailbreak Method Exploiting LLMs' Helpfulness
Evaluated models: Claude Sonnet 4, DeepSeek Chat, DeepSeek R1 Distill Llama 8B+19 more
  • Claude Sonnet 4
  • DeepSeek Chat
  • DeepSeek R1 Distill Llama 8B
  • DeepSeek V3
  • Doubao 1.5 Thinking Pro
  • ERNIE 4.0 Turbo
  • Gemini 2.0 Flash
  • Gemini 2.5 Pro
  • Gemma 3 27B IT
  • GPT-3.5 Turbo
  • GPT-4
  • GPT-4o
  • Llama 3.1 8B
  • Mixtral 8x7B
  • o1
  • o3
  • Phi-2
  • Qwen 2.5 72B Instruct
  • Qwen 3 32B
  • Qwen 3 8B
  • Qwen Omni Turbo
  • Vicuna 7B

Content Concretization Jailbreak

Published Analyzed Source: arXiv

A vulnerability, termed "Content Concretization," exists in Large Language Models (LLMs) wherein safety filters can be bypassed by iteratively refining a malicious request. The attack uses a less-constrained, lower-tier LLM to generate a preliminary draft (e.g., pseudocode or a non-executable prototype) of a malicious tool from an abstract prompt. This "concretized" draft is then passed to a more capable, higher-tier LLM. The higher-tier LLM, when prompted to refine or complete the existing…

Jailbreaking Large Language Models Through Content Concretization
Evaluated models: Claude 3.5 Haiku, Claude 3.5 Sonnet, Claude 3.7 Sonnet+8 more
  • Claude 3.5 Haiku
  • Claude 3.5 Sonnet
  • Claude 3.7 Sonnet
  • Gemini 2.0 Flash
  • Gemini 2.5 Flash
  • Gemini 2.5 Pro
  • GPT-4
  • GPT-4.1
  • GPT-4o
  • GPT-4o Mini
  • o3

Typos Undermine Watermarks

Published Analyzed Source: arXiv

Large Language Model (LLM) inference-time watermarking schemes are vulnerable to evasion via character-level perturbations that disrupt the model's tokenizer. Unlike token-level attacks (e.g., synonym replacement), character-level edits—such as homoglyph substitutions, zero-width character insertions, and typos—force the tokenizer to segment a single semantic unit into multiple sub-word tokens. This fragmentation alters the context window used by the watermarking hashing function (e.g., the…

Character-Level Perturbations Disrupt LLM Watermarks
Evaluated models: Llama 3 8B

Camouflaged Jailbreak Prompts Benchmark

Published Analyzed Source: arXiv

Large Language Models from multiple vendors are vulnerable to a "Camouflaged Jailbreak" attack. Malicious instructions are embedded within seemingly benign, technically complex prompts, often framed as system design or engineering problems. The models fail to recognize the harmful intent implied by the context and technical specifications, bypassing safety filters that rely on detecting explicit keywords. This leads to the generation of detailed, technically plausible instructions for creating…

Behind the Mask: Benchmarking Camouflaged Jailbreaks in Large Language Models
Evaluated models: Gemma 3 4B IT, GPT-4, GPT-4o+2 more
  • Gemma 3 4B IT
  • GPT-4
  • GPT-4o
  • Llama 3.1 8B Instruct
  • Mistral 7B Instruct v0.3

Ethical Dilemma Jailbreak TRIAL

Published Analyzed Source: arXiv

A vulnerability exists in multiple Large Language Models (LLMs) where an attacker can bypass safety alignments by exploiting the model's ethical reasoning capabilities. The attack, named TRIAL (Trolley-problem Reasoning for Interactive Attack Logic), frames a harmful request within a multi-turn ethical dilemma modeled on the trolley problem. The harmful action is presented as the "lesser of two evils" necessary to prevent a catastrophic outcome, compelling the model to engage in utilitarian…

Between a Rock and a Hard Place: The Tension Between Ethical Reasoning and Safety Alignment in LLMs
Evaluated models: Claude 3.7 Sonnet, DeepSeek R1, DeepSeek V3+9 more
  • Claude 3.7 Sonnet
  • DeepSeek R1
  • DeepSeek V3
  • GLM 4 Plus
  • GPT-3.5 Turbo
  • GPT-4 Turbo
  • GPT-4o
  • Llama 2 13B
  • Llama 3 70B Instruct
  • Llama 3.1 8B
  • Qwen 2.5 7B
  • Vicuna 13B v1.5

Prompt Injection Alignment Bypass

Published Analyzed Source: arXiv

Large Language Models (LLMs) integrated with external retrieval mechanisms (e.g., Retrieval-Augmented Generation (RAG), web search, or email processing) are vulnerable to Indirect Prompt Injection. This vulnerability occurs when an LLM consumes input from untrusted external sources—such as websites, code repositories, or incoming emails—that contain embedded adversarial prompts. Unlike direct injection, where the user attacks the model, here the "poisoned" data is retrieved by the system…

Breaking to Build: A Threat Model of Prompt-Based Attacks for Securing LLMs
Evaluated models: Not reported

Knowledge Neuron Jailbreak

Published Analyzed Source: arXiv

Aligned Large Language Models (LLMs) utilizing Transformer architectures are vulnerable to representation-level attacks targeting safety-knowledge neurons within the Multi-Layer Perceptron (MLP) layers. Research indicates that safety decision-making (Rejection vs. Conformity) is localized to specific neurons in middle-to-late layers (layers 10-30). An attacker with white-box access can calculate a "Conformity" direction vector based on the activation differences between benign and harmful…

Unraveling LLM Jailbreaks Through Safety Knowledge Neurons
Evaluated models: Llama 2 7B, Vicuna 7B

Logit Leakage Model Clone

Published Analyzed Source: arXiv

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
Evaluated models: GPT-3.5, Mistral 7B

GCG Code Reasoning Exploit

Published Analyzed Source: arXiv

Large Language Models (LLMs), specifically Qwen2.5-0.5B-Instruct, LLaMA-3.2-1B-Instruct, and GPT-OSS-20B, are vulnerable to gradient-based adversarial attacks, including the Greedy Coordinate Gradient (GCG) algorithm and its annealing-augmented variant, T-GCG. Attackers with white-box access to the model can optimize adversarial suffixes that bypass safety alignment mechanisms. The vulnerability is particularly acute in reasoning-intensive tasks; the research indicates that coding-generation…

The Resurgence of GCG Adversarial Attacks on Large Language Models
Evaluated models: GPT-oss 20B, Llama 3.2 1B Instruct, Qwen 2.5 0.5B Instruct

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.