Topics
Browse posts by category and tag — every topic we cover, with the latest pieces under each.
Tags
- #prompt-injection 9
- #adversarial-ml 8
- #llm-security 8
- #red-teaming 7
- #jailbreaking 6
- #attack-patterns 3
- #supply-chain 3
- #agent-security 2
- #backdoor-attacks 2
- #black-box-attacks 2
- #data-poisoning 2
- #defense 2
- #evasion-attacks 2
- #fine-tuning 2
- #indirect-prompt-injection 2
- #model-security 2
- #adversarial-examples 1
- #adversarial-patches 1
- #adversarial-suffix 1
- #agentic-ai 1
- #ai-attacks 1
- #ai-security 1
- #attack-taxonomy 1
- #benchmarking 1
- #ci-cd 1
- #context-poisoning 1
- #dataset-integrity 1
- #detection 1
- #evasion 1
- #fgsm 1
- #fraud-detection 1
- #function-calling 1
- #garak 1
- #gcg 1
- #gpt-4v 1
- #guardrails 1
- #hugging-face 1
- #indirect-injection 1
- #ip-theft 1
- #llm-attacks 1
- #long-context 1
- #machine-learning-security 1
- #malware-detection 1
- #many-shot 1
- #membership-inference 1
- #memory-attacks 1
- #model-extraction 1
- #model-inversion 1
- #model-poisoning 1
- #model-robustness 1
- #multimodal 1
- #optimization-attacks 1
- #owasp 1
- #persistence 1
- #privacy-attacks 1
- #rag 1
- #rag-security 1
- #regression-testing 1
- #safety-training 1
- #tool-call-hijacking 1
- #training-data 1
- #training-data-extraction 1
- #trojan-ml 1
- #vision-models 1
- #visual-prompt-injection 1
- #vulnerability-taxonomy 1
- #web-scraping 1
- #white-box 1
Categories
Adversarial ML 6 posts
- Evasion Attacks on Production Classifiers: Malware, Spam, FraudDeployed ML classifiers in malware, spam, and fraud detection face evasion attacks where the attacker has a clear payoff.
- Poisoning Web-Scale Training Sets: Split-View and FrontrunningYou don't need to control a model's training pipeline to poison it — you only need to control content the crawler will fetch.
- Adversarial Examples Against Vision Models in 2026Where physical-world adversarial patches and digital attacks stand against modern vision models, what has been hardened, and what red teams should test.
- Model Extraction via Black-Box Query AttacksHow attackers reconstruct model behavior and decision boundaries through query-only access, the economics of the attack, and what stolen models enable.
- Model Inversion and Membership Inference: Extracting LLM DataHow membership inference reveals whether specific data trained a model, and how inversion reconstructs private text from gradients and model outputs.
- Training Data Poisoning and Backdoor Attacks on LLMsA technical deep dive into how adversaries manipulate training datasets and plant hidden backdoors in LLMs, covering triggers, stealth, and detection.
Attack Patterns 5 posts
- Jailbreaking Multimodal Models: Visual Prompt Injection AttacksHow attackers use images, typography, and adversarial perturbations to bypass safety guardrails in multimodal models, and why vision widens the surface.
- LLM Context Window PoisoningHow attackers plant persistent malicious instructions in memory and context, survive summarization, and carry influence across separate LLM sessions.
- Indirect Prompt Injection in RAG PipelinesHow attackers embed malicious instructions in documents that get retrieved into LLM context — and why RAG makes prompt injection a supply-chain problem.
- Supply Chain Attacks on AI Models: Poisoning and BackdoorsHow attackers compromise models before production through dataset poisoning, malicious fine-tuning, and serialization exploits, and how to detect it.
- Tool-Call Hijacking in Agentic SystemsHow attackers exploit the gap between LLM reasoning and function execution to trigger unauthorized tool calls, and why confirmation gaps are the root.
Attack Techniques 4 posts
- How Indirect Prompt Injection WorksHow indirect prompt injection works: attacker instructions hidden in web pages, emails and RAG documents, the attack surface, and what defenders can do.
- LLM Jailbreak Examples: 10 Documented PatternsTen LLM jailbreak examples drawn from published research, with the reported success rates, the mechanism behind each, and the signals that detect them.
- Adversarial Suffixes: A GCG Practitioner GuideA working guide to Greedy Coordinate Gradient search: how it finds adversarial suffixes that bypass alignment, and what the transferability result means.
- Many-Shot Jailbreaking: What the Research ShowsHow hundreds of synthetic compliance examples in a long-context prompt erode safety training, what the published results show, and why patching is hard.
Defense 2 posts
- LLM Jailbreak Defenses: Why Static Filters FailWhy LLM jailbreak defenses that score well on static benchmarks collapse against adaptive attackers, and what an honest robustness evaluation has to measure.
- How to Detect Prompt Injection: Four Approaches RankedInput heuristics, classifier APIs, hidden-state probes, and output monitoring: how to detect prompt injection in production LLM apps, with tradeoffs.
Explainer 2 posts
- Prompt Injection vs Jailbreak: How They Differ and Why It MattersPrompt injection targets your application architecture; jailbreaking targets the model's safety alignment. Confusing them defends the wrong layer.
- Adversarial Examples Explained Simply: How Pixels Fool a ModelA plain-language walkthrough of adversarial examples: what they are, why neural networks fall for them, how FGSM works, and what defenders can do.