Lucene search
+L

141 matches found

Kitploit
Kitploit
โ€ขadded 2026/11/21 12:46 a.m.โ€ข39 views

ai-llm-red-team-handbook

AI / LLM Red Team Field Manual & Consultant's Handbook A comprehensive operational toolkit for conducting AI/LLM red team assessments on Large Language Models, AI agents, RAG pipelines, and AI-enabled applications. This repository provides both tactical field guidance and strategic consulting...

6.3AI score
SaveExploits0References4
Kitploit
Kitploit
โ€ขadded 2026/11/20 9:37 p.m.โ€ข24 views

PS4-5.05-Kernel-Exploit

PS4 5.05 Kernel Exploit Summary In this project you will find a full implementation of the second "bpf" kernel exploit for the PlayStation 4 on 5.05. It will allow you to run arbitrary code as kernel, to allow jailbreaking and kernel-level modifications to the system. This exploit also contains...

6.6AI score
SaveExploits0References3
Kitploit
Kitploit
โ€ขadded 2026/11/20 6:08 p.m.โ€ข9 views

SMT

Beyond the Prompt: Jailbreaking Function-Calling LLMs via Simulated Moderation Traces Introduction This repository contains the official implementation of our paper: Beyond the Prompt: Jailbreaking Function-Calling LLMs via Simulated Moderation Traces If you find this repository useful for your...

6.2AI score
SaveExploits0
Kitploit
Kitploit
โ€ขadded 2026/11/20 5:20 p.m.โ€ข51 views

TRACE

TRACE: Task-Aware Adaptive Self-Evolving Agentic Jailbreaking Official implementation for TRACE: Task-Aware Adaptive Self-Evolving Agentic Jailbreaking. ๐Ÿ“– Overview Large language model LLM agents can autonomously plan, invoke tools, interact with environments, and execute long-horizon workflows...

6.7AI score
SaveExploits0References4
Kitploit
Kitploit
โ€ขadded 2026/11/20 10:12 a.m.โ€ข38 views

dataset

๐Ÿš€ CySecBench: Generative AI-based CyberSecurity-focused Prompt Dataset for Benchmarking Large Language Models ๐Ÿ›ก๏ธ The largest and most comprehensive Generative AI-based CyberSecurity-focused Dataset for Benchmarking Large Language Models ๐ŸŒŸ Overview The CySecBench paper offers: ๐ŸŽฏ A cutting-edge...

6.3AI score
SaveExploits0References12
Kitploit
Kitploit
โ€ขadded 2026/11/20 5:21 a.m.โ€ข9 views

jailbreak-eval-7llms

Jailbreak Evaluation Across 7 LLMs Code, prompts, and results for: Systematic Evaluation of Adversarial Jailbreaking Attacks and Defenses Across Seven Large Language Models Md. Robiul Islam Niloy, Abu Sayed Md. Mostafizur Rahaman. Md. Robiul Islam Niloy: Department of Computer Science and...

6.2AI score
SaveExploits0
Kitploit
Kitploit
โ€ขadded 2026/11/19 11:19 p.m.โ€ข32 views

PS4-5.05-Kernel-Exploit

PS4 5.05 Kernel Exploit Summary In this project you will find a full implementation of the second "bpf" kernel exploit for the PlayStation 4 on 5.05. It will allow you to run arbitrary code as kernel, to allow jailbreaking and kernel-level modifications to the system. This exploit also contains...

6.6AI score
SaveExploits0References4
Packet Storm News
Packet Storm News
โ€ขadded 2026/10/29 12:00 a.m.โ€ข21 views

Systematic Evaluation of Adversarial Jailbreaking Attacks and Defenses across Seven Large Language Models

Large language models LLMs deployed in safety-critical settings must resist adversarial inputs designed to elicit harmful outputs. We present a systematic empirical evaluation of five adversarial jailbreaking attack families---direct requests, roleplay-based jailbreaking, hypothetical framing,...

5.9AI score
SaveExploits0
Packet Storm News
Packet Storm News
โ€ขadded 2026/10/12 12:00 a.m.โ€ข15 views

ATTCK-R: Knowledge-Aware Long-Horizon Jailbreaking for Protected LLMs

As large language models are deployed behind increasingly sophisticated safety mechanisms, evaluating their robustness under realistic adversarial conditions becomes increasingly difficult and critical. Existing jailbreaking evaluations often rely on static prompts, limited interaction horizons, ...

5.8AI score
SaveExploits0
Packet Storm News
Packet Storm News
โ€ขadded 2026/10/05 12:00 a.m.โ€ข14 views

Jailbreaking Open-Weight LLMs Via Random Embedding Perturbations

While open-weight models have enjoyed steady progress in capabilities and wide adoption across multiple domains, their safety remains an important concern. One key feature is the ability to refuse or deflect harmful, malicious, or insensitive prompts. In this paper, we expose safety vulnerabiliti...

5.8AI score
SaveExploits0
Packet Storm News
Packet Storm News
โ€ขadded 2026/10/04 12:00 a.m.โ€ข34 views

Red-TTT: Test-Time Training for Automated Jailbreaking Large Language Models

Large language models remain vulnerable to jailbreaks, and automated red teaming is the standard way to find jailbreaks in large language models at scale. Current methods either draw more samples at test time through search, rewriting, and tree expansion, or train a stronger attacker offline with...

5.9AI score
SaveExploits0
Packet Storm News
Packet Storm News
โ€ขadded 2026/09/28 12:00 a.m.โ€ข21 views

Inference-Layer Security: Defending against Adversarial Inference and Infrastructure Abuse

A Technical Report: Operating a large language model LLM as a service requires more than inference infrastructure: the provider must also defend against adversarial interactions that seek to exploit the service, including jailbreaking for harmful use, sophisticated denial of service, and...

5.8AI score
SaveExploits0
Schneier on Security
Schneier on Security
โ€ขadded 2026/09/23 11:03 a.m.โ€ข50 views

Research on Models Engaging in Genie-Like Behavior

New paper: "Self-Jailbreaking: Language Models Can Reason Themselves Out of Safety Alignment After Benign Reasoning Training." Abstract: We discover a novel and surprising phenomenon of unintentional misalignment in reasoning language models RLMs, which we call self-jailbreaking. Specifically,...

5.9AI score
SaveExploits0
Packet Storm News
Packet Storm News
โ€ขadded 2026/08/11 12:00 a.m.โ€ข19 views

On Understanding, Identifying, and Mitigating Vulnerabilities in Agentic Large Language Models

Large Language Models LLMs have undergone a shift from stateless conversational interfaces to autonomous agents capable of multi-step planning, tool invocation, code execution, and maintaining persistent memory. When these agents operate with real-world privileges---calling APIs, modifying files,...

5.8AI score
SaveExploits0
Packet Storm News
Packet Storm News
โ€ขadded 2026/06/05 12:00 a.m.โ€ข44 views

Beyond Pass/Fail: Using Process Mining to Understand How LLMs Resist (And Fail) Red Team Attacks

Standard AI red teaming evaluations reduce adversarial campaigns to a single binary outcome, attack success rate ASR, not taking into account the sequential structure of how models resist or yield to attacks. We propose applying process mining, a discipline for discovering and analyzing process...

5.4AI score
SaveExploits0
Packet Storm News
Packet Storm News
โ€ขadded 2026/06/04 12:00 a.m.โ€ข181 views

Membrane: A Self-Evolving Contrastive Safety Memory for LLM Agent Defense

Despite advances in safety alignment, large language models remain vulnerable to continuously evolving jailbreaks. Existing fine-tuned safety classifiers cannot adapt to these evolving attacks, while adaptive memory-based guardrails tend to over-refuse benign queries that resemble stored attacks...

5.5AI score
SaveExploits0
Packet Storm News
Packet Storm News
โ€ขadded 2026/06/01 12:00 a.m.โ€ข27 views

MaskForge: Structure-Aware Adaptive Attacks for Jailbreaking Diffusion Large Language Models

Diffusion large language models dLLMs generate text by iteratively denoising partially masked sequences under bidirectional context, exposing a safety surface distinct from autoregressive LLMs. Because mask tokens are native inputs and tokens are committed by confidence rather than position,...

5.8AI score
SaveExploits0
Packet Storm News
Packet Storm News
โ€ขadded 2026/05/27 12:00 a.m.โ€ข28 views

Evolving Skill-Structured Attack Memory Enhances LLM Jailbreaking

Jailbreak attacks on large language models LLMs aim to induce LLMs to produce content that they are expected to refuse. Automated black-box jailbreak generation is especially important for safety evaluation, where the attacker observes only model outputs and needs to automatically search for...

5.8AI score
SaveExploits0
Packet Storm News
Packet Storm News
โ€ขadded 2026/05/26 12:00 a.m.โ€ข51 views

Disentangling Adversarial Prompts: A Semantic-Graph Defense for Robust LLM Security

Large Language Models LLMs are increasingly vulnerable to adversarial prompts that exploit semantic ambiguities to bypass safety mechanisms, resulting in harmful or inappropriate outputs. Such attacks, including jailbreaking and prompt injection, pose significant risks to the integrity and...

5.8AI score
SaveExploits0
Mend
Mend
โ€ขadded 2026/05/20 9:04 a.m.โ€ข6 views

MAI-2024-0047

Large Language Models LLMs are susceptible to optimization-based jailbreaking attacks that exploit index gradients during the iterative generation of adversarial suffixes. The vulnerability arises from the inefficient exploration of the token space in existing methods, such as Greedy Coordinate...

6.3CVSS6AI score
SaveExploits0References1
Rows per page
Query Builder