Before prompt injection attacks on LLMs, blue boxes let hackers make free long-distance phone calls by injecting special tones into the network ... Show more
Story Details
| Last Updated | |
| Total Articles | 1 |
Main Topics
making, modification, usage, and knowledge of tools, machines, techniques, crafts, systems, and methods of organization, or tools and techniques so created
any attempt to expose, alter, disable, destroy, steal or gain unauthorized access to or make unauthorized use of a computer system
Similar to This
Previous
I ran a local LLM on my phone for a month, and it handled 90% of the prompts I used to send to Claude and ChatGPT
xda-developers.com/ran-local-llm-on-phone-it-handled-90-percent-of-prompts-i-send-to-claude-chatgpt/
Prompt Injection: Why Hackers No Longer Need Code to Steal Your Data: By tricking AI chatbots into ignoring their own rules, attackers are bypassing enterprise ...
pcmag.com/explainers/prompt-injection-why-hackers-no-longer-need-code-to-steal-your-data
Inside AI Prompt Security: Why Stopping Every LLM Exploit Is Impossible: Because AI understands human language, hackers can trick models using clever phrasing ...
pcmag.com/explainers/inside-ai-prompt-security-why-stopping-every-llm-exploit-is-impossible
LLMs respond differently to harmful prompts when AI watermarking is used: SynthID can cause models to follow harmful instructions they would otherwise refuse.
arstechnica.com/security/2026/09/ai-text-watermarking-can-make-models-more-vulnerable-to-adversarial-prompts/
Prompt injection ranks No. 1 with OWASP and No. 12 in the incident record. The attack itself is invisible to a scan.
venturebeat.com/security/prompt-injection-ranks-no-1-with-owasp-and-no-12-in-the-incident-record-the-attack-itself-is-invisible-to-a-scan
Grok exfiltrates user data when malicious instructions are encrypted: Cryptographic Context Injection is only the latest way to break an LLM safety guardrail.
arstechnica.com/security/2026/08/grok-exfiltrates-user-data-when-malicious-instructions-are-encrypted/
What is context bombing, a new AI defence technique turning hackers’ tricks against them?
indianexpress.com/article/technology/artificial-intelligence/what-is-context-bombing-ai-technique-hackers-10793703/
Prompt Injection Attacks Are Thwarting AI Hacking Agents: “Context bombing” tricks malicious AI agents into shutting down before they can do harm.
arstechnica.com/security/2026/07/now-defenders-are-embracing-the-prompt-injection-too/
Hackers can use 9 of the most popular AI tools to assemble massive botnets: HalluSquatting" weaponizes LLMs' inability to say "I don't know."
arstechnica.com/security/2026/07/hackers-can-use-9-of-the-most-popular-ai-tools-to-assemble-massive-botnets/
dlvr.it Jun 30
Security researchers tricked LLMs into giving them cocaine recipes by abusing role models for prompt injection
theregister.com/ai-and-ml/2026/06/30/security-researchers-tricked-llms-into-giving-them-cocaine-recipes-by-abusing-role-models-for-prompt-injection/5264115
thecybersecguru.com Jun 01
Instagram Meta AI Vulnerability: How Hackers Bypassed 2FA with Prompt Injection | The CyberSec Guru
thecybersecguru.com/news/instagram-meta-ai-vulnerability-account-recovery-exploit/
github.com May 26
GitHub - 9hannahnine-jpg/arc-gate: Arc Gate — LLM proxy with prompt injection detection. Bendex Geometry.
github.com/9hannahnine-jpg/arc-gate
github.com Apr 23
GitHub - 9hannahnine-jpg/arc-sentry: Whitebox prompt injection detector for self-hosted open-weight LLMs. Deployment-specific behavioral monitor; calibrates on ...
github.com/9hannahnine-jpg/arc-sentry
AI bots are ignoring their programming and giving hackers superpowers: Hackers recently used mainstream AI chatbots to steal data on 195 million Mexican citizens ...
thestar.com.my/tech/tech-news/2026/03/11/ai-bots-are-ignoring-their-programming-and-giving-hackers-superpowers
AI allows hackers to identify anonymous social media accounts, study finds: New research suggests tech behind AI platforms such as ChatGPT makes it easier to ...
theguardian.com/technology/2026/mar/08/ai-hackers-social-media-accounts-study
How our AI bots are ignoring their programming and giving hackers superpowers: Welcome to the age of AI hacking, in which the right prompts make amateurs into ...
latimes.com/business/story/2026-03-05/how-our-ai-bots-are-ignoring-their-programming-giving-hackers-superpowers
greaterwrong.com Feb 08
Prompt injection in Google Translate reveals base model behaviors behind task-specific fine-tuning
greaterwrong.com/posts/tAh2keDNEEHMXvLvz/prompt-injection-in-google-translate-reveals-base-model
This Gemini Calendar trick turns a simple invite into a privacy nightmare: Researchers found that when users ask Gemini about their schedule, it can be tricked ...
androidauthority.com/gemini-google-calendar-exploit-3634125/
AI agents open door to new hacking threats: AI agents are programs that use artificial intelligence chatbots to do the work humans do online ...
thestar.com.my/tech/tech-news/2025/11/11/ai-agents-open-door-to-new-hacking-threats
Tech Times Oct 26 23
Honor Magic 6: Open Apps Using its Eye-Tracking Feature—Specs and MORE: Honor added an eye-tracking feature for the Magic 6, and you can use this to open apps ...
techtimes.com/articles/297976/20231026/honor-magic-6-open-apps-using-eye-tracking-feature—specs-more.htm
Next