MacGregor Voyage Data Recorder (VDR) G4e

ADVISORY SUMMARY Successful exploitation of these vulnerabilities could result in an attacker gaining administrator access to the device. 2. RECOMMENDED PRACTICES CISA recommends users take defensive measures to minimize the risk of exploitation of these vulnerabilities. Minimize network...

Protecting On-Device AI Inference: A Systematic Review of Attacks and Defence Mechanisms

The need for secure and private Artificial Intelligence AI and Machine Learning ML on edge and mobile devices has increased the necessity of protecting the architecture of these systems from threats to both security and privacy. With an ever-increasing number of pre-trained AI models being used o...

Exploit for CVE-2026-0211

ISU-SecOps Nginx QUIC RCE Lab Modern web sunucularındaki Ngi...

AI Security Research Should Better Incentivize Defense Research

This work examines an imbalance in artificial intelligence AI security research: the field tends to produce more work on attacking AI systems than on defending them. Drawing on related academic papers, we find biased attack-to-defense ratios across subfields, including federated learning, speech...

Are Frontier LLMs Ready for Cybersecurity? Evidence for Vertical Foundation Models from Dual-Mode Vulnerability Benchmarks

We evaluate whether frontier LLMs are ready for cybersecurity through a dual-mode benchmark: white-box function-level vulnerability detection VulnLLM-R, across C/Java/Python and black-box web application security testing five production-style applications with 118 ground-truth vulnerabilities...

Exploit for Untrusted Pointer Dereference in Microsoft

CVE-2026-40369: Defensive Analysis of the 12-Byte Windows Kern...

Alleged Kimwolf Botmaster ‘Dort’ Arrested, Charged in U.S. and Canada

Canadian authorities on Wednesday arrested a 23-year-old Ottawa man on suspicion of building and operating Kimwolf , a fast spreading Internet-of-Things botnet that enslaved millions of devices for use in a series of massive distributed denial-of-service DDoS attacks over the past six months...

Pretraining Data Exposure in Large Language Models: A Survey of Membership Inference, Data Contamination, and Security Implications

Large Language Models LLMs have become the predominant paradigm in NLP, advancing both research and industry. As model sizes and pretraining data grow, concerns about Pretraining Data Exposure PDE increase due to the scale and opacity of training datasets. PDE refers to determining whether specif...

Data Brokers’ and AI Firms’ Opt-Out Forms Are Built to Fail, Report Finds

A new study finds AI companies, defense firms, and dating apps are among 38 data collectors allegedly using manipulative design to confuse users while collecting their data...

ScadaBR

ADVISORY SUMMARY Successful exploitation of these vulnerabilities could allow an attacker to perform unauthenticated remote code execution. 2. RECOMMENDED PRACTICES CISA recommends users take defensive measures to minimize the risk of exploitation of these vulnerabilities. Minimize network...

Loaded Dice: Solving the Non-Selection Problem for Scalable Probabilistic RowHammer Defense

DRAM scaling has exacerbated the RowHammer vulnerability. To counter this, JEDEC recently introduced Per Row Activation Counting PRAC with the Alert Back-Off protocol as an optional DDR5 feature. While promising, PRAC requires per-row counter cells that incur area overhead, and updating them on...

Microsoft is changing Edge’s plaintext password behavior

Microsoft said it will change Edge’s password handling as a “defense‑in‑depth” measure. Originally, Edge decrypted the entire saved‑password store on startup and kept all credentials resident in process memory in clear text for the whole browser session, regardless of whether a given credential w...

Be Kind, Rewrite: Benign Projections Via Rewriting Defend against LLM Data Poisoning Attacks

Large language models LLMs are highly susceptible to backdoor attacks BAs, wherein training samples are poisoned using trigger-based harmful content. Furthermore, existing defenses have proven ineffective when extensively tested across BA patterns. To better combat BAs, we explore the use of LLM...

Backdooring Masked Diffusion Language Models

Masked diffusion language models MDLMs are emerging as a compelling new paradigm for text generation, but their training-time security remains largely unexplored. Existing backdoor attacks on Gaussian diffusion models or autoregressive language models do not directly apply to MDLMs because MDLMs...

Speed Kills: Exploring Confused Deputy Attacks through Edge AI Accelerators

AI Accelerator AIA are specialized hardware e.g., Tensor Processing Unit TPU, that enable optimal and efficient execution of AI applications and on-device inference. The growing demand for AI applications has led to the widespread adoption of AIAs on Edge or embedded devices on Edge or embedded...

A Red Teaming Framework for Evaluating Robustness of AI-Enabled Security Orchestration, Automation, and Response Systems

AI-enabled Security Orchestration, Automation, and Response SOAR systems increasingly employ autonomous agents for cyber defense, yet their resilience to adaptive adversaries is underexplored. We introduce an autonomous red teaming framework that integrates large language models LLMs with...

Defense in depth for autonomous AI agents

Designing Secure Autonomous AI Agents with Defense in Depth AI agents are moving beyond assistance and into action. Instead of generating content, they invoke tools, modify data, trigger workflows, and operate across systems with increasing autonomy. This shift changes the security problem...

Defense in depth for autonomous AI agents

Designing Secure Autonomous AI Agents with Defense in Depth AI agents are moving beyond assistance and into action. Instead of generating content, they invoke tools, modify data, trigger workflows, and operate across systems with increasing autonomy. This shift changes the security problem...

anti-hacking

🛡️ anti-hacking: Comprehensive Defensive Security Knowledge Ba...

CVE-2026-44232

The CVE-2026-44232 entry concerns the Node.js library dssrf . The vulnerability, described across the CVE and related records, is that prior to version 1.3.0 every IPv6 category bypasses the is_url_safe check, enabling potential SSRF bypasses. The issue affects the dssrf functionality that guards...