Security
5,347 items in 29 lists
-
Gandalf gandalf.lakera.ai
Your goal is to make Gandalf reveal the secret password for each level. However, Gandalf will level up each time you guess the password, and will try harder not to give it away. Can you beat level 7? (There is a bonus level 8).
-
ChatGPT Plugins: Data Exfiltration via Images & Cross Plugin Request Forgery embracethered.com
This post shows how a malicious website can take control of a ChatGPT chat session and exfiltrate the history of the conversation.
-
Don't you (forget NLP): Prompt injection with control characters in ChatGPT dropbox.tech
A look into how to achieve prompt injection from control characters from Dropbox.
-
Prompt-Injection Cascades in a Multi-Agent Enterprise (ATLAS) doi.org
Forensic study in which one poisoned support ticket drives four agents across three model families to a fraudulent transfer in 17 of 18 trials, with no model jailbroken. Argues the failure is topological rather than per-model. Synthetic data, CC BY 4.0.
-
Authority Framing in Agentic CI/CD (RELAY) doi.org
Pre-registered factorial study of a five-agent CI/CD pipeline built from five production LLMs. A fabricated "pre-approved, do not re-review" claim gets secret-exfiltration code shipped in up to 55% of runs, and roughly 80% of laundered pull requests pass a capable LLM code…
-
Learn Prompting discord.com
Discord server from Learn Prompting.
-
Why content-based prompt-injection detection has a structural blind spot dev.to
Walks through a disguised "already-scanned, classified DATA" annotation that passes both a regex layer and a local LLM classifier (qwen2.5:3b and 14b), with the gap pinned as a failing test. Detection is necessary but not sufficient.
-
CrowdStrike AI Unlocked crowdstrike.com
Released Feb 2026, designed to train security, developer, and AI teams on prompt injection against increasingly capable agents. Built by CrowdStrike's Counter Adversary Operations team.
-
Indirect Prompt Injection Attacks: Hidden AI Risks crowdstrike.com
CrowdStrike's Dec 2025 analysis of IPI TTPs targeting enterprise GenAI, including attacker-controlled document poisoning, RAG context manipulation, and practical detection signals for SOC workflows.
-
Prompt Injection Cheat Sheet: How To Manipulate AI Language Models blog.seclify.com
A prompt injection cheat sheet for AI bot integrations.
-
Improving LLM Security Against Prompt Injection: AppSec Guidance For Pentesters and Developers – Part 2 blog.includesecurity.com
Understanding Transformer Models (especially attention), Causes and How Do We Stop Prompt Injection.
-
Improving LLM Security Against Prompt Injection: AppSec Guidance For Pentesters and Developers blog.includesecurity.com
Using Role Based APIs to Minimize the Risk of Prompt Injection and 13 Guidelines for Writing System Prompts that Minimize the Risk of Prompt Injection.
-
MITRE ATLAS atlas.mitre.org
MITRE's adversarial ML threat matrix formally cataloging direct and indirect prompt injection as core adversary techniques, enabling integration into enterprise threat modelling and purple team exercises.
-
The Landscape of Prompt Injection Threats in LLM Agents (SoK) arxiv.org
Feb 2026 systematization-of-knowledge paper with a unified taxonomy covering attack payload strategies (heuristic vs. optimisation-based) and defense intervention stages (text, model, execution). Introduces the AgentPI benchmark for context-dependent agent tasks that all prior…
-
Securing AI Agents Against Prompt Injection Attacks arxiv.org
Nov 2025 benchmark of 847 adversarial test cases across 5 attack categories against 7 LLMs. The combined defense framework reduces attack success from 73.2% to 8.7% while retaining 94.3% of baseline task performance.
-
Oct 2025 paper systematically breaking 12 published defenses using gradient descent, RL, random search, and human-guided exploration. Most defenses originally claimed near-zero attack success rates; adaptive attacks exceeded 90% against all of them.
-
Prompt Injection 2.0: Hybrid AI Threats arxiv.org
Jul 2025 paper showing how prompt injections now combine with XSS, CSRF, AI worm propagation, and multi-agent infections to evade traditional WAFs entirely. Evaluates Preamble's classifier, data-tagging, and RL-based defenses against these hybrid scenarios.
-
ToolHijacker: Prompt Injection Attack to Tool Selection in LLM Agents arxiv.org
Apr 2025 paper introducing a no-box attack that injects a malicious tool document into an agent's tool library to consistently hijack tool selection. Finds that StruQ, SecAlign, DataSentinel, and perplexity detection are all insufficient defenses.
-
Jailbreaking LLMs' Safeguard with Universal Magic Words for Text Embedding Models arxiv.org
Discovers that text embedding models have severely biased output distributions, and exploits this to find universal adversarial suffixes ("magic words") that bypass embedding-based LLM safeguards. Attacks transfer across models and languages; a train-free debiasing defense is…
-
Universal and Transferable Adversarial Attacks on Aligned Language Models arxiv.org
This paper introduces a simple and efficient attack method that enables aligned language models to generate objectionable content with high probability, highlighting the need for improved prevention techniques in large language models. The generated adversarial prompts are…
-
This paper explores the concept of Indirect Prompt Injection attacks on Large Language Models (LLMs) through their integration with various applications. It identifies significant security risks, including remote data theft and ecosystem contamination, present in both…
-
Agents Rule of Two: A Practical Approach to AI Agent Security ai.meta.com
Meta's Oct 2025 framework stating that agents must satisfy no more than two of: (A) processing untrustworthy inputs, (B) access to sensitive data, (C) ability to change state externally, a deterministic architectural approach to bounding blast radius.
-
Attention Tracker: Detecting Prompt Injection Attacks in LLMs aclanthology.org
NAACL 2025 Findings paper detecting prompt injection by tracking attention distribution shifts, with no modification to the underlying model required, making it deployable as a wrapper on any LLM.
-
AI/LLM Exploitation Challenges academy.8ksec.io
AI, ML, and LLMs CTF Challenges.
-
Detection Engineering Twitter List | Zack Allen x.com
A Twitter list of Detection Engineering thought leaders.
-
Cloud Threat Landscape | Wiz threats.wiz.io
A cloud detection engineering-focused database, that lists threat actors known to have compromised cloud environments, the tools and techniques in their arsenal, and the technologies they prefer to target.
-
SOCLabs soc-labs.top
A lab for blue teamers and detection engineers, with real threat data and support for popular SIEM query languages, enabling hands-on learning and practice in detection rule writing and threat hunting.
-
Sigma rule converter sigconverter.io
An opensource tool that can convert detection content for use with most SIEMs.
-
Open Cybersecurity Schema Framework (OCSF) schema.ocsf.io
An opensource security data source and event schema.
-
Blue-team-as-Code - the Spiral of Joy | Den Iuzvyk, Oleg Kolesnikov sansorg.egnyte.com
Blue-Team-as-Code: Lessons From Real-world Red Team Detection Automation Using Logs.
-
Detection Maturity Level (DML) Model | Ryan Stillions ryanstillions.blogspot.com
Defines and describes 8 different levels of an organization's threat detection program maturity.
-
Rulehound rulehound.com
An index of publicly available and open-source threat detection rulesets.
-
Detection at Scale Podcast | Jack Naglieri podcasts.apple.com
A detection engineering-focused podcast featuring many thought leaders in the specialization.
-
ATT&CK Navigator | MITRE mitre-attack.github.io
MITRE's open-source tool that can be used to track detection coverage, visibility, and other efforts and their relationship to the ATT&CK framework.
-
Prioritizing Detection Engineering | Ryan McGeehan medium.com
A longtime detection engineer outlines how a detection engineering program should be built from the ground up.
-
Threat Detection Maturity Framework | Haider Dost of Snowflake medium.com
A maturity matrix to measure the success of your threat detection program.
-
Detection Development Lifecycle | Haider Dost et al. medium.com
Snowflake’s implementation of the Detection Development Lifecycle.
-
MITRE ATT&CK Data Sources Blog Post medium.com
MITRE describes various data sources and how they relate to the TTPs found in the MITRE ATT&CK framework.
-
DETT&CT: MAPPING YOUR BLUE TEAM TO MITRE ATT&CK™ mbsecure.nl
Outlines a methodology measuring security data visibility and detection coverage against the MITRE ATT&CK framework.
-
Windows Logging Cheatsheets malwarearchaeology.com
Multiple cheatsheets outlined recommendations for Windows Event logging at various levels of granularity.
-
Living Off the Living Off the Land lolol.farm
A collection of resources for thriving off the land.
-
Cyber Kill Chain | Lockheed Martin lockheedmartin.com
Lockheed Martin's framework that outlines the 7 stages commonly observed in a cyber attack.
-
Microsoft XDR Advanced Hunting Schema learn.microsoft.com
To help with multi-table queries, you can use the advanced hunting schema, which includes tables and columns with event information and details about devices, alerts, identities, and other entity types.
-
Azure Defender for Cloud Security Alerts learn.microsoft.com
A list of all Azure Security for Cloud Alerts, their descriptions, and associated data sources.
-
InnerWarden innerwarden.com
Autonomous security agent for Linux with real-time threat detection and response via 38 eBPF hooks, 48 detectors, and 23 correlation rules.
-
Detection Engineering AI Maturity Framework | Brendan Chamberlain infosecb.github.io
A community framework with four maturity levels across ten dimensions for assessing how organizations apply AI and LLMs across a detection engineering program, from foundations through the detection lifecycle.
-
Panther Labs Detection Rules github.com
Panther Lab's native detection rules.
-
Open Threat Informed Detection Engineering aka OpenTide' github.com
an all-in-one Detection Engineering Operations framework created and maintained by the European Commission to convert your CTI into an actionable detection coverage graph combining threat vectors with detection objectives, and manage your entire detection library from a central…
-
Linux auditd Detection Ruleset github.com
Linux auditd ruleset that produces telemetry required for threat detection use cases.
-
Splunk ES Correlation Searches Best Practices | OpsTune github.com
A highly detailed guide to producing high quality detection content in the Splunk Enterprise Security app.
- next page of items loading…
