All news with #ai red teaming tag

🔒 Palo Alto Networks has launched Prisma AIRS in the Singapore cloud region to provide locally hosted, AI-native cybersecurity for organizations adopting generative AI and agentic workflows. The regional landing delivers capabilities across AI Model Security, AI Red Teaming, AI Runtime Security, and AI Agent SSPM, addressing risks such as prompt injection, model tampering and sensitive data leaks. Local hosting supports data residency, regulatory alignment and improved performance for enterprises in Singapore.

⚠️ CrowdStrike's latest Global Threat Report finds that in 2025 attackers required an average of just 29 minutes to gain full network access, a roughly 65% acceleration from the prior year. The fastest measured breakout dropped to 27 seconds, and some intrusions began exfiltrating data within four minutes of initial access. Researchers link the shift to a steep rise in AI-assisted operations — attackers using AI grew 89% — citing examples such as the LLM-based malware Lamehug, AI-generated credential-extraction scripts, and AI-crafted identities used for insider-style campaigns. Adam Meyers warns defenders must be faster than attackers as AI compresses the window between intent and execution.

🔍 In the January 27, 2026 OpenSSL security release, twelve previously unknown zero-day vulnerabilities were announced, all originally discovered and responsibly disclosed by our AI research system, AISLE. Ten of the issues were assigned CVE-2025 identifiers and two received CVE-2026 identifiers. One high-profile finding, CVE-2025-15467, is a stack buffer overflow with a NIST CVSS v3 score of 9.8 and has already produced public exploits. Five of the twelve accepted fixes were directly proposed by AISLE, and several bugs dated back to 1998–2000, including code inherited from the original SSLeay implementation.

🔐 CrowdStrike has launched AI Unlocked: Decoding Prompt Injection, an interactive online challenge hosted via Falcon Encounter hands-on labs that immerses security teams in attacker-style prompt injection scenarios. Participants progress through three virtual rooms—Command Center, Data Gateway, and Nexus—using prompt injection techniques to convince the simulated supervisor SAIGE to reveal secret phrases while earning higher scores for brevity and efficiency. The exercise aims to convert abstract AI security risks into practical lessons, helping teams recognize attack patterns and the need for defensive guardrails.

🤖 Unit 42 of Palo Alto Networks found that low-skilled cybercriminals are using LLMs to script extortion campaigns, a technique researchers call vibe extortion. In one case, an intoxicated attacker recorded a threat video and read an AI-generated script verbatim, gaining a professional tone despite lacking technical skill. The report warns that AI is acting as a force multiplier—speeding reconnaissance, crafting convincing lures, and automating extortion tasks—raising risk even from unsophisticated actors and urging immediate mitigations.

⚠️Microsoft warns that legitimate companies are embedding hidden instructions in 'Summarize with AI' buttons to bias chatbot memory and recommendations. The Defender Security Research Team calls this AI Recommendation Poisoning, finding more than 50 distinct prompts from 31 firms across 14 industries that attempt to make assistants 'remember' and favor a source in future conversations. The technique uses prefilled URL parameters and turnkey tools like CiteMET, and Microsoft advises users and organizations to audit assistant memory, avoid untrusted AI links, hover over AI buttons, and hunt for suspicious prompt keywords.

🛡️Wiz has built a 257-challenge benchmark suite to evaluate AI agents across five offensive security domains: zero-day discovery, CVE detection, API security, web security, and cloud security. Tests run inside isolated Docker containers with no per-challenge timeouts, use deterministic scoring rubrics, and give each agent three attempts per challenge. The vendor-agnostic framework measures capability rather than throttling, and in Wiz's announcement Claude Code on Claude Opus 4.6 narrowly topped the trials, with Gemini 3 Pro placing second.

🔍 Microsoft Defender Security Research Team describes an AI-assisted workflow that converts unstructured threat reports into actionable detection insights. The system uses LLMs with Retrieval Augmented Generation to extract candidate TTPs, metadata, and required telemetry, then normalizes behaviors to MITRE ATT&CK. Extracted TTPs are compared to a standardized detection catalog via vector similarity search and LLM validation to surface likely coverage and gap recommendations. Human-in-the-loop review, deterministic prompts, and evaluation loops are emphasized to ensure accuracy before operational changes.

🛡️ Check Point Research and Sysdig examined a sophisticated Linux malware framework called VoidLink and concluded a single developer used an AI coding agent to accelerate development. The Zig-based project grew to over 88,000 lines by December 2025 and exhibits systematic artifacts — consistent debug formatting, placeholder data like "John Doe", uniform _v3 API patterns, and exhaustive JSON templates — that suggest heavy LLM involvement. No real-world infections have been observed, but researchers warn this case demonstrates how AI can rapidly lower the barrier to creating advanced offensive tooling.

🧠 Check Point Research reports that the VoidLink Linux cloud malware framework displays clear evidence of being developed predominantly with AI assistance. The actor used an AI-centric IDE, TRAE, and its assistant TRAE SOLO to produce specification documents, sprint plans, and large portions of source code, which reached a working state within days. Exposed development artifacts — including TRAE helper files and an open directory of source and docs — allowed researchers to match generated specs to the recovered code and reproduce the development workflow, leading Check Point to conclude this is a notable example of AI-driven malware development.

🛡️ OpenAI says it is expanding a "defense in depth" strategy to limit misuse of its frontier AI models, warning they could be used to develop zero-day exploits or aid complex intrusion operations. The company announced a new Frontier Risk Council, broader guardrails, external red‑teaming, and a trusted access program for vetted customers testing defensive use cases. OpenAI also plans to scale its Aardvark Agentic Security Researcher beta to scan codebases and recommend mitigations.

🔍 Researchers used a new benchmark, SCONE-bench, to train AI agents to find and produce exploits against historically compromised smart contracts. On 405 real-world contracts from 2020–2025, Claude Opus 4.5, Claude Sonnet 4.5, and GPT-5 generated exploits valued at $4.6 million. In simulated tests against 2,849 recently deployed contracts the agents discovered two novel zero-day vulnerabilities and created exploits worth $3,694, with GPT-5 incurring $3,476 in API costs. The findings show autonomous, profitable exploitation is technically feasible and emphasize the need for proactive AI-driven defense.

🛡️ Generative AI is rapidly reshaping cybersecurity by amplifying both attackers' and defenders' capabilities. Adversaries leverage models for coding assistance, phishing and social engineering, anti-analysis techniques (including prompts hidden in DNS) and vulnerability discovery, with AI-assisted elements beginning to appear in malware while still needing significant human oversight. Defenders use GenAI to triage threat data, speed incident response, detect code flaws, and augment analysts through MCP-style integrations. As models shrink and access widens, both risk and defensive opportunity are likely to grow.

🔒 Generative AI introduces new attack surfaces that alter trust relationships between users, applications and models. Siemens' pentest and security teams differentiate Offensive Security (targeted technical pentests) from Red Teaming (broader organizational simulations of real attackers). Traditional ML risks such as image or biometric misclassification remain relevant, but experts now single out prompt injection as the most serious threat — simple crafted inputs can leak system prompts, cause misinformation, or convert innocuous instructions into dangerous command injections.

🔬 Netskope Threat Labs tested whether large language models can generate operational malware by asking GPT-3.5-Turbo, GPT-4 and GPT-5 to produce Python for process injection, AV/EDR termination and virtualization detection. GPT-3.5-Turbo produced malicious code quickly, while GPT-4 initially refused but could be coaxed with role-based prompts. Generated scripts ran reliably on physical hosts, had moderate success in VMware, and performed poorly in AWS Workspaces VDI; GPT-5 raised success rates substantially but also returned safer alternatives because of stronger safeguards. Researchers conclude LLMs can create useful attack code but still struggle with reliable evasion and cloud adaptation, so full automation of malware remains infeasible today.

🛍️ Black Friday shopping is increasingly fraught with staged discounts and manipulated prices, but large language models (LLMs) can help shoppers cut through the noise. Use AI like ChatGPT, Claude, or Gemini to build a wish list, track historical prices, compare alternatives, and vet sellers quickly. The article provides step-by-step prompts for price analysis, seller verification, local-market queries, and model-specific requests, and recommends security measures such as using a separate card and installing Kaspersky Premium to reduce fraud risk.

🔒 Cybersecurity researchers disclosed an attempted intrusion against a major U.S. real-estate firm that leveraged the emerging Tuoni C2 and red-team framework. The campaign, observed in mid-October 2025, used Microsoft Teams impersonation and a PowerShell loader that fetched a BMP-steganographed payload from kupaoquan[.]com and executed shellcode in memory. That sequence spawned TuoniAgent.dll, which contacted a C2 server but ultimately failed to achieve its goals. The incident highlights the risk of freely available red-team tooling and AI-assisted code generation being abused by threat actors.

🧭 Hugo Selbie presents a practical framework for evaluating modern multi-step AI agents, emphasizing that final-output metrics alone miss silent failures arising from incorrect reasoning or tool use. He recommends defining clear, measurable success criteria up front and assessing agents across three pillars: end-to-end quality, process/trajectory analysis, and trust & safety. The piece outlines mixed evaluation methods—human review, LLM-as-a-judge, programmatic checks, and adversarial testing—and prescribes operationalizing these checks in CI/CD with production monitoring and feedback loops.

🤖 AI-driven adversarial bots are rapidly amplifying attackers' capabilities, enabling autonomous pen testing and large-scale credential abuse that many organizations aren't prepared to detect or remediate. Tools like XBOW and Hexstrike-AI demonstrate how agentic systems can discover zero-days and coordinate complex operations at scale. Defenders must adopt continuous, context-rich approaches such as digital twins for real-time threat modeling rather than relying on incremental automation.

🔍 Cisco AI Defense's report shows open-weight large language models remain vulnerable to adaptive, multi-turn adversarial attacks even when single-turn defenses appear effective. Using over 1,000 prompts per model and analyzing 499 simulated conversations of 5–10 exchanges, researchers found iterative strategies such as Crescendo, Role-Play and Refusal Reframe drove failure rates above 90% in many cases. The study warns that traditional safety filters are insufficient and recommends strict system prompts, model-agnostic runtime guardrails and continuous red-teaming to mitigate risk.