Agentic Safety and Ecosystem Architect, Trust and Safety Google | USA | On-site – View job details As an Agentic Safety and Ecosystem Architect, Trust and Safety, you will define safety controls and permission models for autonomous agents on Android, helping ensure actions are reviewed before execution and access to sensitive data requires explicit consent.…
Tag: safety
Global Security News
Cisco study finds major frontier models susceptible to multi-turn prompt injection attacks
Single-turn attack success rates are not a reliable benchmark for model safety, Cisco concludes.
AI, Global Security News, Risk Management
AI models more vulnerable than claimed when faced with iterative attacks
CISOs relying on LLM runtime guardrails and official safety scores when making security decisions about their organizations’ AI usage and model selection are due for a wakeup call. According to a new study from Cisco, frontier models from OpenAI, Anthropic, Google, xAI, and Amazon have significantly worse risk profiles when pressured in multi-turn attacks compared…
AI, Apps, Global Security News, Risk Management
Microsoft releases open-source tools to operationalize AI agent safety
Microsoft has open-sourced two new tools aimed at bringing AI safety checks much earlier into the agent development lifecycle. The tools, called Rampart and Clarity, were announced this week as part of Microsoft’s broader push to operationalize safety engineering for agentic AI. “We built these tools because we believe that AI safety has to become…
AI, Global Security News
7 Key Features That Make Secure Browsers Safer
Secure Browsers boost safety with tracking blocks, fingerprint protection, session control, and real-time threat defense against modern web attacks.
AI, Global Security News, Government & Policy, privacy
LAPD Deployed Drones to Spy on No Kings Protest
The Los Angeles Police Department deployed drones intended for public safety uses to surveil a No Kings rally and a protest against the Trump administration’s anti-immigrant campaign, flight data reveals. Last year, the LAPD launched its “Drone as First Responder” program with a clearly articulated goal: to protect and even save lives. The pilot program…
AI, Cybersecurity, Global Security News, Government & Policy, privacy, Risk Management
Social media bans might steer kids into riskier corners of the internet
Governments are moving to block children under 16 from social media in the name of safety. But once these measures move from policy to practice, they raise a harder question: what happens when protecting kids requires collecting more data than ever before and may put them at greater risk? Age checks spark debate over privacy…
AI, Apps, Compliance, Global Security News, malware, Network Security, privacy, Risk Management
Aura Business Debuts BYOD Security Solution for MSPs
AI-powered online safety platform Aura has introduced a new business security solution to help shrink the unmanaged device gap that exists in today’s security stacks. The new identity-centric bring your own device solution built for MSPs Aura Business for MSPs is a new identity-centric BYOD security solution designed to protect businesses and employees. It allows…
Exploits, Global Security News
Claude Code Can Be Manipulated via CLAUDE.md to Run SQL Injection Attacks
LayerX researchers have discovered how to bypass Claude Code’s safety rules using the CLAUDE.md file. This exploit allows…
AI, APAC, Apps, Compliance, Cybersecurity, Data Breaches, Endpoint, Exploits, Global Security News, malware, Risk Management
ClickFix Meets AI: A Multi-Platform Attack Targeting macOS in the Wild
For years, macOS environments carried an aura of relative safety. Not immunity, but lower priority in the threat landscape. That perception has aged about as well as an unpatched server. The reality in 2026 is very different. Apple devices now make up a significant share of corporate endpoints. And they sit in the hands of the people attackers most want…
AI, APAC, Apps, Compliance, Cybersecurity, Data Breaches, Endpoint, Exploits, Global Security News, malware, Risk Management
ClickFix Meets AI: A Multi-Platform Attack Targeting macOS in the Wild
For years, macOS environments carried an aura of relative safety. Not immunity, but lower priority in the threat landscape. That perception has aged about as well as an unpatched server. The reality in 2026 is very different. Apple devices now make up a significant share of corporate endpoints. And they sit in the hands of the people attackers most want…
AI, Cybersecurity, Global Security News
Basic Tips To Ensure Online Safety
This post will show you basic tips to ensure online safety. Increased online activity brings with it a necessity for improved online safety practices. Nowadays, many of us rely on the internet for all sorts of things. Communication, banking, entertainment, and career progression often depend on how well we use the internet. But some of…
AI, Compliance, Data Breaches, Endpoint, Exploits, Global Security News, malware, Network Security, privacy
Jamf warns of massive app insecurities
“Be wary then; best safety lies in fear,” said Laertes to sister Ophelia in William Shakespeare’s Hamlet. That’s a quote that should be on the desk of every business professional, as the digital environment is full of danger. Jamf provides us with a good look at what’s becoming a dangerous environment for Mac and iOS…
Compliance, Cybersecurity, Global Security News
Construction Safety Compliance Software: Keep Your Site Safe and Audit‑Ready Every Day
Discover how Construction Safety Compliance Software: Keep Your Site Safe and Audit‑Ready Every Day can enhance safety and streamline your site’s compliance. Key Highlights Embrace construction safety software to streamline your site safety and compliance management. In Australia, some of the most popular construction safety compliance software solutions include HammerTech, SiteDocs, and Procore, which are…
AI, Global Security News, Risk Management
Make OpenAI’s models misbehave and earn a reward
OpenAI’s public Safety Bug Bounty program focuses on AI abuse and safety risks across its products. The goal is to support safe and secure systems and reduce the risk of misuse that could lead to harm. This program complements the Security Bug Bounty. It accepts reports of abuse and safety risks that do not meet…
AI, Global Security News
OpenAI Expands Bug Bounty to Cover AI Abuse and ‘Safety’ Concerns
OpenAI’s Safety Bug Bounty program seeks to address AI safety vulnerabilities beyond traditional security flaws
AI, Global Security News, Risk Management
Zetifi Launches Connected Fleet Safety Platform To Reinforce Driver and Vehicle Safety at Work
COMPANY NEWS: The missing link in driver safety, Connected Fleet Safety integrates telematics, agentic AI and Microsoft 365 to manage WHS business risk and bolster safer, smarter fleet management across Australia
AI, Global Security News
The World’s First AI-Powered Scam Detector, Norton Genie, Now in ChatGPT
Get instant scam checks and trusted Cyber Safety advice from Norton without leaving your ChatGPT conversation
AI, Global Security News
4chan shrugs off UK regulator, refuses to pay £520,000 over online safety violations
The U.K.’s media regulator Ofcom fined 4chan £450,000 under the Online Safety Act for failing to introduce age checks to stop children from accessing pornographic content on its platform. 4chan is an online forum notorious for its extreme right-wing content, gory videos, and non-consensual pornography. The regulator ordered the company to introduce age assurance measures…
AI, Data Breaches, Global Security News
900,000 contact records exposed in Aura data breach
Aura, the online safety service, confirmed that an unauthorized party accessed about 900,000 records, mostly names and email addresses from a marketing tool linked to a company it acquired in 2021. The incident occurred as a result of a targeted phone phishing attack that tricked one of the employees. Aura believes that contact information related…
AI, Global Security News, Network Security
Researchers Discover Major Security Gaps in LLM Guardrails
Palo Alto Networks’ Unit 42 has developed a successful attack to bypass safety guardrails in popular generative AI tools
AI, china, Data Breaches, Exploits, Global Security News, Government & Policy, Politics, privacy, Russia
Congress Is Considering Abolishing Your Right to Be Anonymous Online
Sen. Marsha Blackburn, R-Tenn., speaks at a rally in support of the Kids Online Safety Act on Dec. 10, 2024, in Washington, D.C. Photo: Jemal Countess/Getty Images for Accountable Tech In August 2024, the Biden administration hosted hundreds of influencers at the White House for the first-ever Creator Economy Conference. Neera Tanden, a senior Biden adviser,…
AI, Global Security News
Government Agencies Raise Alarms About Use of Elon Musk’s Grok Chatbot
Warnings about xAI’s safety and reliability preceded the Pentagon’s decision to approve Grok for use in classified settings.
Global Security News
Microsoft fixes bug that blocked Google Chrome from launching
Microsoft has fixed a known issue causing its Family Safety parental control service to block Windows users from launching Google Chrome and other web browsers. […]
AI, Artificial Intelligence, Generative AI, Security, Cybersecurity, Data Breaches, Exploits, Global Security News, Risk Management
Single prompt breaks AI safety in 15 major language models
A single benign-sounding prompt can systematically strip safety guardrails from major language and image models, raising fresh questions about the durability of AI alignment when models are customized for enterprise use, according to Microsoft research. The technique, dubbed GRP-Obliteration, weaponizes a common AI training method called Group Relative Policy Optimization, normally used to make models…
Global Security News
Australian Workplace Safety Investments Not Improving Outcomes
Rapid Global today releases a Workplace Safety report exposing the growing disconnect between safety strategy and worker experience in Australia.
AI, CISO, Cybersecurity, Don't miss, features, Global Security News, Hot stuff, News, Risk Management
United Airlines CISO on building resilience when disruption is inevitable
Aviation runs on complex digital systems built for stability, safety, and long lifecycles. That reality creates a unique cybersecurity challenge for airlines, where disruption can quickly become an operational and public trust crisis. In this Help Net Security interview, Deneen DeFiore, VP and CISO at United Airlines, explains how the company approaches modernization without compromising…
AI, CISO, Cybersecurity, Don't miss, features, Global Security News, Hot stuff, News, Risk Management
United Airlines CISO on building resilience when disruption is inevitable
Aviation runs on complex digital systems built for stability, safety, and long lifecycles. That reality creates a unique cybersecurity challenge for airlines, where disruption can quickly become an operational and public trust crisis. In this Help Net Security interview, Deneen DeFiore, VP and CISO at United Airlines, explains how the company approaches modernization without compromising…
AI, Android, android security, Apps, Exploits, Global Security News, Risk Management
Rust in Android: move fast and fix things
Posted by Jeff Vander Stoep, Android Last year, we wrote about why a memory safety strategy that focuses on vulnerability prevention in new code quickly yields durable and compounding gains. This year we look at how this approach isn’t just fixing things, but helping us move faster. The 2025 data continues to validate the approach,…
AI, Cybersecurity, Global Security News, privacy
Accelerating adoption of AI for cybersecurity at DEF CON 33
Posted by Elie Bursztein and Marianna Tishchenko, Google Privacy, Safety and Security Team Empowering cyber defenders with AI is critical to tilting the cybersecurity balance back in their favor as they battle cybercriminals and keep users safe. To help accelerate adoption of AI for cybersecurity workflows, we partnered with Airbus at DEF CON 33 to host…
AI, Compliance, Cybersecurity, Data Breaches, Global Security News, privacy
Red flags, leaked chats, and a final farewell
The viral women-only dating safety app Tea, built to flag red flags, gets flagged itself – after leaking over 70,000 private images and chat logs. We are talking full-on selfies, ID docs, private DMs, and a dash of 4chan creepiness. Yikes. Plus, Carole takes us down memory lane as she hangs up her co-host mic…