AI Útoky

AI Útoky

30.01.2026	LLM Jacking	LLM jacking is an attack technique that cybercriminals use to manipulate and exploit an enterprise’s cloud-based LLMs (large language models). LLM jacking involves stealing and selling cloud account credentials to enable malicious access to an enterprise’s LLMs while the victim unknowingly covers the consumption costs.	ATTACK	AI
20.01.2026	Semantic Attack	Weaponizing Calendar Invites: A Semantic Attack on Google Gemini	ATTACK	AI
06.12.2025	HashJack Attack	HashJack Attack Targets AI Browsers and Agentic AI Systems	ATTACK	AI
29.10.2025	AI-targeted Cloaking Attack	OpenAI’s new browser Atlas falls for AI-targeted Cloaking Attack	ATTACK	AI
31.08.2025	Design Patterns for Securing LLM Agents against Prompt Injections	Large Language Models (LLMs) are becoming integral components of complex software systems, where they serve as intelligent agents that can interpret natural language instructions, make plans, and execute actions through external tools and APIs	ATTACK	AI
24.06.2025	Context Poisoning Jailbreak	Echo Chamber: A Context-Poisoning Jailbreak That Bypasses LLM Guardrails	ATTACK	AI
30.04.2025	Context Compliance Attack	(CCA), a jailbreak technique that involves the adversary injecting a "simple assistant response into the conversation history" about a potentially sensitive topic that expresses readiness to provide additional information	ATTACK	AI
30.04.2025	Policy Puppetry Attack	a prompt injection technique that crafts malicious instructions to look like a policy file, such as XML, INI, or JSON, and then passes it as input to the large language model (LLMs) to bypass safety alignments and extract the system prompt	ATTACK	AI
30.04.2025	Memory INJection Attack	(MINJA), which involves injecting malicious records into a memory bank by interacting with an LLM agent via queries and output observations and leads the agent to perform an undesirable action	ATTACK	AI
16.04.2025	Multi-Stage Phishing Attack Exploits Gamma	Attackers exploit Gamma in a multi-stage phishing attack using Cloudflare Turnstile and AiTM tactics to evade detection and steal Microsoft credentials.	ATTACK	AI
19.03.2025	Rules File Backdoor	New Vulnerability in GitHub Copilot and Cursor: How Hackers Can Weaponize Code Agents	ATTACK	AI
01.05.2024	MCP Prompt Injection	MCP Prompt Injection: Not Just For Evil	ATTACK	AI
04.03.2024	ComPromptMized	ComPromptMized: Unleashing Zero-click Worms that Target GenAI-Powered Applications	ATTACK	AI
28.11.2023	Prompt Injection Attack	A prompt injection attack is a type of cyberattack where a hacker enters a text prompt into a large language model (LLM) or chatbot, which is designed to enable the user to perform unauthorized actions.	ATTACK	AI