AI agents break rules in unexpected ways 2025-12-09 at 08:31 By Mirko Zorz AI agents are starting to take on tasks that used to be handled by people. These systems plan steps, call tools, and carry out actions without a person approving every move. This shift is raising questions for security leaders. A new research […]
AI agents break rules in unexpected ways Read More »
New image signature can survive cropping, stop deepfakes from hijacking trust 2025-12-09 at 08:02 By Sinisa Markovic Deepfake images can distort public debate, fuel harassment, or shift a news cycle before anyone checks the source. A new study from researchers at the University of Pisa examines one specific part of this problem. They introduced a
New image signature can survive cropping, stop deepfakes from hijacking trust Read More »
NVIDIA research shows how agentic AI fails under attack 2025-12-08 at 09:56 By Sinisa Markovic Enterprises are rushing to deploy agentic systems that plan, use tools, and make decisions with less human guidance than earlier AI models. This new class of systems also brings new kinds of risk that appear in the interactions between models,
NVIDIA research shows how agentic AI fails under attack Read More »
Building the missing layers for an internet of agents 2025-12-05 at 08:59 By Anamarija Pogorelec Cybersecurity teams are starting to think about how large language model agents might interact at scale. A new paper from Cisco Research argues that the current network stack is not prepared for this shift. The work proposes two extra layers
Building the missing layers for an internet of agents Read More »
A day in the life of the internet tells a bigger story 2025-12-04 at 08:43 By Sinisa Markovic On any given day, the internet carries countless signals that hint at how networks behave behind the scenes. Researchers from RIPE NCC and several universities found a way to capture a detailed snapshot of that activity by
A day in the life of the internet tells a bigger story Read More »
AI vs. you: Who’s better at permission decisions? 2025-12-04 at 08:04 By Sinisa Markovic A single tap on a permission prompt can decide how far an app reaches into a user’s personal data. Most of these calls happen during installation. The number of prompts keeps climbing, and that growing pressure often pushes people into rushed
AI vs. you: Who’s better at permission decisions? Read More »
Offensive cyber power is spreading fast and changing global security 2025-12-01 at 08:36 By Sinisa Markovic Offensive cyber activity has moved far beyond a handful of major powers. More governments now rely on digital operations to project influence during geopolitical tension, which raises new risks for organizations caught in the middle. A new policy brief
Offensive cyber power is spreading fast and changing global security Read More »
Social data puts user passwords at risk in unexpected ways 2025-11-28 at 09:08 By Anamarija Pogorelec Many CISOs already assume that social media creates new openings for password guessing, but new research helps show what that risk looks like in practice. The findings reveal how much information can be reconstructed from public profiles and how
Social data puts user passwords at risk in unexpected ways Read More »
New observational auditing framework takes aim at machine learning privacy leaks 2025-11-28 at 08:34 By Sinisa Markovic Machine learning (ML) privacy concerns continue to surface, as audits show that models can reveal parts of the labels (the user’s choice, expressed preference, or the result of an action) used during training. A new research paper explores
New observational auditing framework takes aim at machine learning privacy leaks Read More »
Small language models step into the fight against phishing sites 2025-11-26 at 08:31 By Sinisa Markovic Phishing sites keep rising, and security teams are searching for ways to sort suspicious pages at speed. A recent study explores whether small language models (SLMs) can scan raw HTML to catch these threats. The work reviews a range
Small language models step into the fight against phishing sites Read More »
Aircraft cabin IoT leaves vendor and passenger data exposed 2025-11-25 at 08:34 By Sinisa Markovic The expansion of IoT devices in shared, multi-vendor environments, such as aircraft cabins, has created tension between the benefits of data collaboration and the risks to passenger privacy, vendor intellectual property, and regulatory compliance. A new study finds that even
Aircraft cabin IoT leaves vendor and passenger data exposed Read More »
The privacy tension driving the medical data shift nobody wants to talk about 2025-11-24 at 08:02 By Anamarija Pogorelec Most people assume their medical data sits in quiet storage, protected by familiar rules. That belief gives a sense of safety, but new research argues that the world around healthcare data has changed faster than the
The privacy tension driving the medical data shift nobody wants to talk about Read More »
Research shows identity document checks are missing key signals 2025-11-21 at 10:06 By Anamarija Pogorelec Most CISOs spend their time thinking about account takeover and phishing, but identity document fraud is becoming a tougher challenge. A new systematic review shows how attackers are pushing past old defenses and how detection models are struggling to keep
Research shows identity document checks are missing key signals Read More »
Security gap in Perplexity’s Comet browser exposed users to system-level attacks 2025-11-20 at 17:56 By Zeljka Zorz There is a serious security problem inside Comet, the AI-powered agentic browser made by Perplexity, SquareX researchers say: Comet’s MCP API allows the browser’s built-in (but hidden from the user) extensions to issue commands directly to a user’s
Security gap in Perplexity’s Comet browser exposed users to system-level attacks Read More »
Google Play Store’s privacy practices still confuse Android users 2025-11-20 at 08:05 By Sinisa Markovic Privacy rules like GDPR and CCPA are meant to help app stores be clearer about how apps use your data. But in the Google Play Store, those privacy sections often leave people scratching their heads. A new study looks at
Google Play Store’s privacy practices still confuse Android users Read More »
BlueCodeAgent helps developers secure AI-generated code 2025-11-20 at 08:05 By Sinisa Markovic When AI models generate code, they deliver power and risk at the same time for security teams. That tension is at the heart of the new tool called BlueCodeAgent, designed to help developers and security engineers defend against code-generation threats. Why code generation
BlueCodeAgent helps developers secure AI-generated code Read More »
The long conversations that reveal how scammers work 2025-11-19 at 09:08 By Sinisa Markovic Online scammers often take weeks to build trust before making a move, which makes their work hard to study. A research team from UC San Diego built a system that does the patient work of talking to scammers at scale, and
The long conversations that reveal how scammers work Read More »
How attackers use patience to push past AI guardrails 2025-11-18 at 08:44 By Anamarija Pogorelec Most CISOs already assume that prompt injection is a known risk. What may come as a surprise is how quickly those risks grow once an attacker is allowed to stay in the conversation. A new study from Cisco AI Defense
How attackers use patience to push past AI guardrails Read More »
The privacy panic around machine learning is overblown 2025-11-18 at 08:43 By Sinisa Markovic We often hear warnings about how machine learning (ML) models may expose sensitive information tied to their training data. The concern is understandable. If a model was trained on personal records, it may seem reasonable to assume that releasing it could
The privacy panic around machine learning is overblown Read More »
Los Alamos researchers warn AI may upend national security 2025-11-14 at 09:25 By Sinisa Markovic For decades, the United States has built its defense posture around predictable timelines for technological progress. That assumption no longer holds, according to researchers at Los Alamos National Laboratory. Their paper argues that AI is advancing so quickly that the
Los Alamos researchers warn AI may upend national security Read More »