#llm-security
-
How Indirect Prompt Injection Works
How indirect prompt injection works: attacker instructions hidden in web pages, emails and RAG documents, the attack surface, and what defenders can do.
-
LLM Jailbreak Defenses: Why Static Filters Fail
Why LLM jailbreak defenses that score well on static benchmarks collapse against adaptive attackers, and what an honest robustness evaluation has to measure.
-
LLM Jailbreak Examples: 10 Documented Patterns
Ten LLM jailbreak examples drawn from published research, with the reported success rates, the mechanism behind each, and the signals that detect them.
-
Prompt Injection vs Jailbreak: How They Differ and Why It Matters
Prompt injection targets your application architecture; jailbreaking targets the model's safety alignment. Confusing them defends the wrong layer.
-
How to Detect Prompt Injection: Four Approaches Ranked
Input heuristics, classifier APIs, hidden-state probes, and output monitoring: how to detect prompt injection in production LLM apps, with tradeoffs.
-
OWASP Top 10 LLM Explained: Every Entry and What to Fix
The OWASP Top 10 for LLM Applications 2025 explained: every entry, what it means in production, what the revision changed, and which fixes return most.
-
Adversarial Suffixes: A GCG Practitioner Guide
A working guide to Greedy Coordinate Gradient search: how it finds adversarial suffixes that bypass alignment, and what the transferability result means.
-
Tool-Call Hijacking in Agentic Systems
How attackers exploit the gap between LLM reasoning and function execution to trigger unauthorized tool calls, and why confirmation gaps are the root.