Assessing the Role of AI in Zero Trust

By 2025, Zero Trust has evolved from a conceptual framework into an essential pillar of modern security. No longer merely theoretical, it's now a requirement that organizations must adopt. A robust, defensible architecture built on Zero Trust principles does more than satisfy baseline regulatory...

QSAF: a Novel Mitigation Framework for Cognitive Degradation in Agentic AI

We introduce Cognitive Degradation as a novel vulnerability class in agentic AI systems. Unlike traditional adversarial external threats such as prompt injection, these failures originate internally, arising from memory starvation, planner recursion, context flooding, and output suppression. Thes...

Manipulation Attacks by Misaligned AI: Risk Analysis and Safety Case Framework

Frontier AI systems are rapidly advancing in their capabilities to persuade, deceive, and influence human behaviour, with current models already demonstrating human-level persuasion and strategic deception in specific contexts. Humans are often the weakest link in cybersecurity systems, and a...

Exploiting Jailbreaking Vulnerabilities in Generative AI to Bypass Ethical Safeguards for Facilitating Phishing Attacks

The advent of advanced Generative AI GenAI models such as DeepSeek and ChatGPT has significantly reshaped the cybersecurity landscape, introducing both promising opportunities and critical risks. This study investigates how GenAI powered chatbot services can be exploited via jailbreaking techniqu...

From Semantic Web and MAS to Agentic AI: a Unified Narrative of the Web of Agents

The concept of the Web of Agents WoA, which transforms the static, document-centric Web into an environment of autonomous agents acting on users' behalf, has attracted growing interest as large language models LLMs become more capable. However, research in this area is still fragmented across...

4 Arrested Over Scattered Spider Hacking Spree

Plus: An “explosion” of AI-generated child abuse images is taking over the web, a Russian professional basketball player is arrested on ransomware charges, and more...

Why AppSec and CloudSec Belong Together in the Age of AI

AI accelerates development— and risk shouldn't be a blocker to innovation. Bridging AppSec and CloudSec with shared context and workflows is key to keeping up...

Autonomous AI-Based Cybersecurity Framework for Critical Infrastructure: Real-Time Threat Mitigation

Critical infrastructure systems, including energy grids, healthcare facilities, transportation networks, and water distribution systems, are pivotal to societal stability and economic resilience. However, the increasing interconnectivity of these systems exposes them to various cyber threats,...

Clio-X: AWeb3 Solution for Privacy-Preserving AI Access to Digital Archives

As archives turn to artificial intelligence to manage growing volumes of digital records, privacy risks inherent in current AI data practices raise critical concerns about data sovereignty and ethical accountability. This paper explores how privacy-enhancing technologies PETs and Web3 architectur...

SEO Poisoning Campaign Targets 8,500+ SMB Users with Malware Disguised as AI Tools

Cybersecurity researchers have disclosed a malicious campaign that leverages search engine optimization SEO poisoning techniques to deliver a known malware loader called Oyster aka Broomstick or CleanUpLoader. The malvertising activity, per Arctic Wolf, promotes fake websites hosting trojanized...

Hiding Prompt Injections in Academic Papers

Academic papers were found to contain hidden instructions to LLMs: It discovered such prompts in 17 articles, whose lead authors are affiliated with 14 institutions including Japan's Waseda University, South Korea's KAIST, China's Peking University and the National University of Singapore, as wel...

Red Teaming AI Red Teaming

Red teaming has evolved from its origins in military applications to become a widely adopted methodology in cybersecurity and AI. In this paper, we take a critical look at the practice of AI red teaming. We argue that despite its current popularity in AI governance, there exists a significant gap...

Evaluating the Critical Risks of Amazon'S Nova Premier under the Frontier Model Safety Framework

Nova Premier is Amazon's most capable multimodal foundation model and teacher for model distillation. It processes text, images, and video with a one-million-token context window, enabling analysis of large codebases, 400-page documents, and 90-minute videos in a single prompt. We present the fir...

A week in security (June 23 – June 29)

Last week on Malwarebytes Labs: Gmail’s multi-factor authentication bypassed by hackers to pull off targeted attacks Thousands of private camera feeds found online. Make sure yours isn’t one of them Sextortion email scammers increase their "Hello pervert" money demands Many data brokers are faili...

The Democratization of Phishing: Popularity of PhaaS platforms on the rise

The Democratization of Phishing: Popularity of PhaaS Platforms on the Rise By Ryan Slaney · June 30, 2025 The phishing industry is being profoundly reshaped by the surge of Phishing-as-a-Service PhaaS platforms. These accessible, often Artificial Intelligence AI-powered, offerings are democratizi...

Facebook's New AI Tool Asks to Upload Your Photos for Story Ideas, Sparking Privacy Concerns

Facebook, the social network platform owned by Meta, is asking for users to upload pictures from their phones to suggest collages, recaps, and other ideas using artificial intelligence AI, including those that have not been directly uploaded to the service. According to TechCrunch, which first...

Cybercriminal abuse of large language models

Cybercriminals are continuing to explore artificial intelligence AI technologies such as large language models LLMs to aid in their criminal hacking activities. Some cybercriminals have resorted to using uncensored LLMs or even custom-built criminal LLMs for illicit purposes. Advertised features ...

cosmos-predict2 (>=1.0.6 <=1.0.9), frankenstein-model (>=5.1.6 <=5.3.9) +8 more potentially affected by CVE-2025-23264 via megatron-core (=0.10.0)

megatron-core PYPI version =0.10.0 is affected by a known vulnerability. The following packages have a transitive dependency on megatron-core and may be impacted: - cosmos-predict2 =1.0.6, =5.1.6, =1.0.0, =2.0.8, =1.0.0, =1.0.0, =1.0.0, =1.0.0, =1.0.0, =1.0.0, =1.2.9 Source cves: CVE-2025-23264...

cosmos-predict2 (>=1.0.6 <=1.0.9), frankenstein-model (>=5.1.6 <=5.3.9) +8 more potentially affected by CVE-2025-23265 via megatron-core (=0.10.0)

megatron-core PYPI version =0.10.0 is affected by a known vulnerability. The following packages have a transitive dependency on megatron-core and may be impacted: - cosmos-predict2 =1.0.6, =5.1.6, =1.0.0, =2.0.8, =1.0.0, =1.0.0, =1.0.0, =1.0.0, =1.0.0, =1.0.0, =1.2.9 Source cves: CVE-2025-23265...

Google Adds Multi-Layered Defenses to Secure GenAI from Prompt Injection Attacks

Google has revealed the various safety measures that are being incorporated into its generative artificial intelligence AI systems to mitigate emerging attack vectors like indirect prompt injections and improve the overall security posture for agentic AI systems. "Unlike direct prompt injections,...