Searched for
PROMPT INJECTION VULNERABILITIES
$200K gone in seconds: How a Morse code message manipulated Grok into a $200,000 crypto transfer—what this shocking incident means for AI securityThe incident underscores rising risks at the intersection of artificial intelligence and automated financial systems, especially when bots ...- Claude Opus 4.7 released: Here’s what’s new in the latest version of Anthropic's flagship AI modelAnthropic on Thursday released Claude Opus 4.7, the latest upgrade in its flagship Opus AI model family. Users will now be able to delegate...
- Beyond KYC: Why digital trust needs real-time intelligenceAshok Hariharan of IDfy argues that digital trust must evolve beyond one-time KYC to continuous, intelligence-led risk assessment across th...
- AI agent future is coming: OpenClaw creatorOpenClaw, an AI agent tool by Peter Steinberger, is making waves. It performs real-life tasks, heralding the 'year of agents'. While exciti...
- New-age cos feel market ire; Apple's budget-friendly India pushNew-age companies fell on Monday as a sharp market selloff dragged equities lower. This and more in today's ETtech Top 5.
- AI-led vibe coding amplifying security and governance fearsExecutives warned that risks such as prompt injection, data exposure and vulnerabilities in widely used models could trigger large-scale im...
- AI agents open door to new hacking threatsExperts warn that AI agents, designed to perform online tasks for users, could be hijacked by hackers through “query injection” attacks. Th...
- Huntington's disease cure is possible through new treatment, reveals study. Check symptoms, what causes illnessHuntington's disease findings were announced last month in a news release from uniQure, the company that sponsored the research.
- AI deployment needs strong checks, mate!AI tools should be efficient and effective assistants rather than unsupervised decision-makers, experts say.
- Biased output, privacy violation, unauthorised data sharing due to AI can have serious ramifications for India IncInternal auditors in India are raising concerns about the rapid adoption of AI without adequate controls and ethical safeguards. Companies ...
- Study flags critical AI vulnerabilities in fintech, healthcare appsThe research, conducted by cybersecurity startup Astra Security, shows how LLMs can be manipulated to leak sensitive data or make dangerous...
- Gemini Forged like Achilles: Google Shields Gemini, with Powerful Security Advancements.Google DeepMind enhances Gemini models' security. The upgrade addresses 'indirect prompt injections'. These injections exploit AI's data ac...
- Charging your phone at the airport? Security expert says you might be inviting hackers inA security expert has warned travelers against using public charging stations at airports, citing major risks like malware installation, da...
- Smiley sabotage: How 'emojis' are becoming AI’s weakest link in cybersecurity?Emojis, commonly used for adding emotion to digital communication, are now identified as potential tools for manipulating AI systems. Resea...
- Not all AI apps are safe; tech prone to attacks: Cyber advisoryIn its advisory, the Computer Emergency Response Team of India (CERT-In), the national technology arm to guard the Indian Internet space an...
- Fitch cuts BoI viability rating, maintains negative outlook on Indian banksThe rating also reflects the bank's somewhat weaker capital flexibility than its peers.
- Odisha working on Rs 700 crore project to mitigate flood furyWith frequent floods ravaging the state, Odisha government today said it was implementing a Rs 700 crore project to mitigate flood fury on ...
- India may be affected due to renewed euro-zone crisis: RBIIndia and other developing countries could be adversely affected due to increased risk aversion and slowdown in global capital flows.
- RBI not likely to hike interest rates; CRR cut unlikelyThe RBI is likely to take a detour from its hawkish policy stance of hiking interest rates and pause after the sharp correction in IIP data.
- Users at risk of IE bug, warns MicrosoftMicrosoft has issued a warning about an Internet Explorer bug that might hack into and take control of unprotected computers.
Load More
