TeleAI-Safety: A Comprehensive LLM Jailbreaking Benchmark Towards Attacks, Defenses, and Evaluations

While the deployment of large language models LLMs in high-value industries continues to expand, the systematic assessment of their safety against jailbreak and prompt-based attacks remains insufficient. Existing safety evaluation benchmarks and frameworks are often limited by an imbalanced...

The Road of Adaptive AI for Precision in Cybersecurity

Cybersecurity's evolving complexity presents unique challenges and opportunities for AI research and practice. This paper shares key lessons and insights from designing, building, and operating production-grade GenAI pipelines in cybersecurity, with a focus on the continual adaptation required to...

Sunbird DCIM dcTrack and Power IQ

RISK EVALUATION Successful exploitation of these vulnerabilities could allow an attacker to gain unauthorized access or steal credentials. 2. RECOMMENDED PRACTICES CISA recommends users take defensive measures to minimize the risk of exploitation of these vulnerabilities, such as: Minimize...

MAXHUB Pivot

RISK EVALUATION Successful exploitation of this vulnerability could allow an attacker to request a password reset and gain unauthorized access to the account. 2. RECOMMENDED PRACTICES CISA recommends users take defensive measures to minimize the risk of exploitation of this vulnerability, such...

A Practical Honeypot-Based Threat Intelligence Framework for Cyber Defence in the Cloud

In cloud environments, conventional firewalls rely on predefined rules and manual configurations, limiting their ability to respond effectively to evolving or zero-day threats. As organizations increasingly adopt platforms such as Microsoft Azure, this static defense model exposes cloud assets to...

Safe2Harm: Semantic Isomorphism Attacks for Jailbreaking Large Language Models

Large Language Models LLMs have demonstrated exceptional performance across various tasks, but their security vulnerabilities can be exploited by attackers to generate harmful content, causing adverse impacts across various societal domains. Most existing jailbreak methods revolve around Prompt...

Fixing a Slow SOC: Top 3 Solutions that Actually Work

Smarter SOC performance with faster triage, proactive defence, and a unified stack powered by instant alert context from ANY.RUN to cut MTTD and MTTR...

📄 Microsoft Windows 11 build 10.0.22631.6199 Privilege Escalation

Microsoft Windows 11 build 10.0.22631.6199 proof of concept tool that implements a notorious local privilege escalation technique on Windows. The code implements a task scheduler/DLL sideloading attack to achieve UAC bypass / privilege escalation by forcing the trusted SilentCleanup task to load...

How to build forward-thinking cybersecurity teams for tomorrow

We are witnessing something unprecedented in cybersecurity: the democratization of advanced cyberattack capabilities. What once required nation-state resources sophisticated social engineering, polymorphic malware, coordinated infrastructure now fits in a prompt window. AI is no longer a futurist...

How to build forward-thinking cybersecurity teams for tomorrow

We are witnessing something unprecedented in cybersecurity: the democratization of advanced cyberattack capabilities. What once required nation-state resources sophisticated social engineering, polymorphic malware, coordinated infrastructure now fits in a prompt window. AI is no longer a futurist...

Empower CISOs with Visibility, Agility, Compliance, and Strategic ROI

Learn how Akamai Prolexic Network Cloud Firewall allows CISOs to manage risk, resilience, and reputation by delivering visibility, agility, and proactive defense...

Mirion Medical EC2 Software NMIS BioDose

RISK EVALUATION Successful exploitation of these vulnerabilities could allow an attacker to modify program executables, gain access to sensitive information, gain unauthorized access to the application, and execute arbitrary code. 2. RECOMMENDED PRACTICES CISA recommends users take defensive...

COGNITION: From Evaluation to Defense against Multimodal LLM CAPTCHA Solvers

This paper studies how multimodal large language models MLLMs undermine the security guarantees of visual CAPTCHA. We identify the attack surface where an adversary can cheaply automate CAPTCHA solving using off-the-shelf models. We evaluate 7 leading commercial and open-source MLLMs across 18...

Securing Large Language Models (LLMs) from Prompt Injection Attacks

Large Language Models LLMs are increasingly being deployed in real-world applications, but their flexibility exposes them to prompt injection attacks. These attacks leverage the model's instruction-following ability to make it perform malicious tasks. Recent work has proposed JATMO, a task-specif...

An Empirical Study on the Security Vulnerabilities of GPTs

Equipped with various tools and knowledge, GPTs, one kind of customized AI agents based on OpenAI's large language models, have illustrated great potential in many fields, such as writing, research, and programming. Today, the number of GPTs has reached three millions, with the range of specific...

CVE-2025-62593 Ray is vulnerable to RCE via Safari & Firefox Browsers through DNS Rebinding Attack

Ray is an AI compute engine. Prior to version 2.52.0, developers working with Ray as a development tool can be exploited via a critical RCE vulnerability exploitable via Firefox and Safari. This vulnerability is due to an insufficient guard against browser-based attacks, as the current defense us...

How BAS Helps Threat Exposure Management: A Complete Guide

Your vulnerability scanner just produced a report with hundreds of "critical" CVEs. Now what? For most security teams, this is where the guessing game begins. You know you can't fix everything at once, so you're forced to make tough calls based on CVSS scores and gut feelings, all while hoping yo...

A Safety and Security Framework for Real-World Agentic Systems

This paper introduces a dynamic and actionable framework for securing agentic AI systems in enterprise deployment. We contend that safety and security are not merely fixed attributes of individual models but also emergent properties arising from the dynamic interactions among models, orchestrator...

Charting the future of SOC: Human and AI collaboration for better security

Security operations centers are under pressure from unprecedented scale and complexity. Speed, precision, and consistency matter more than ever, and AI is everywhere—but hype alone doesn’t solve the challenge. This blog shares our journey and insights from building autonomous AI agents for MDR...

Ashlar-Vellum Cobalt, Xenon, Argon, Lithium, Cobalt Share (Update A)

RISK EVALUATION Successful exploitation of these vulnerabilities could allow an attacker to disclose information or execute arbitrary code. 2. RECOMMENDED PRACTICES CISA recommends users take defensive measures to minimize the risk of exploitation of these vulnerabilities, such as: Minimize...