News

Trend Micro’s Robert McArdle says cybercriminals use of AI is far more limited than many realize, and pales in comparison to defenders’ use of the technology

In Anlehnung an Albert Einstein ließe sich wohl sagen, dass der kriminelle Einfallsreichtum der Menschen unendlich ist. Der neueste Trend Quishing beweist jedenfalls einmal wieder, dass die Cyberkriminellen keine Möglichkeit auslassen. Die Experten von Sophos X-Ops haben sich den neuesten Hype der Infiltration über QR-Codes genauer angesehen. Wenn Cyberkriminelle ihre Phishing-Methoden mit eigentlich ganz harmlosen […]

Sophos hat heute den Report „Pacific Rim“ veröffentlicht, der detailliert ein jahrelanges Katz-und-Maus-Spiel aus Angriffs- und Verteidigungsoperationen mit mehreren staatlich unterstützten Cybercrime-Gruppierungen aus China beschreibt. Im Fokus der Attacken standen dabei Cybersicherheits-Perimetergeräte, darunter Sophos Firewalls. Die Angreifer nutzten eine Reihe von Kampagnen mit neuartigen Exploits und maßgeschneiderter Malware, um Tools zur Durchführung von Überwachung, Sabotage […]

Interesting research: “Hacking Back the AI-Hacker: Prompt Injection as a Defense Against LLM-driven Cyberattacks“:

Large language models (LLMs) are increasingly being harnessed to automate cyberattacks, making sophisticated exploits more accessible and scalable. In response, we propose a new defense strategy tailored to counter LLM-driven cyberattacks. We introduce Mantis, a defensive framework that exploits LLMs’ susceptibility to adversarial inputs to undermine malicious operations. Upon detecting an automated cyberattack, Mantis plants carefully crafted inputs into system responses, leading the attacker’s LLM to disrupt their own operations (passive defense) or even compromise the attacker’s machine (active defense). By deploying purposefully vulnerable decoy services to attract the attacker and using dynamic prompt injections for the attacker’s LLM, Mantis can autonomously hack back the attacker. In our experiments, Mantis consistently achieved over 95% effectiveness against automated LLM-driven attacks. To foster further research and collaboration, Mantis is available as an open-source tool: this https URL.

This isn’t the solution, of course. But this sort of thing could be part of a solution.

Really interesting research: “An LLM-Assisted Easy-to-Trigger Backdoor Attack on Code Completion Models: Injecting Disguised Vulnerabilities against Strong Detection“:

Abstract: Large Language Models (LLMs) have transformed code com-
pletion tasks, providing context-based suggestions to boost developer productivity in software engineering. As users often fine-tune these models for specific applications, poisoning and backdoor attacks can covertly alter the model outputs. To address this critical security challenge, we introduce CODEBREAKER, a pioneering LLM-assisted backdoor attack framework on code completion models. Unlike recent attacks that embed malicious payloads in detectable or irrelevant sections of the code (e.g., comments), CODEBREAKER leverages LLMs (e.g., GPT-4) for sophisticated payload transformation (without affecting functionalities), ensuring that both the poisoned data for fine-tuning and generated code can evade strong vulnerability detection. CODEBREAKER stands out with its comprehensive coverage of vulnerabilities, making it the first to provide such an extensive set for evaluation. Our extensive experimental evaluations and user studies underline the strong attack performance of CODEBREAKER across various settings, validating its superiority over existing approaches. By integrating malicious payloads directly into the source code with minimal transformation, CODEBREAKER challenges current security measures, underscoring the critical need for more robust defenses for code completion.

Clever attack, and yet another illustration of why trusted AI is essential.

A cyber-attack targeting telematics provider Microlise has disrupted tracking services for key clients like DHL and Serco

Organizations remain unprepared to defend against known and predictable attacks like ransomware

Winos4.0 malware, derived from Gh0strat, targets Windows users via game-related applications, enabling remote control of affected systems

The Nigerian police have arrested 113 foreign individuals and their 17 Nigerian collaborators for their alleged involvement in high-level cybercrimes

Google wants to ensure a smooth transition towards required MFA across all Google Cloud accounts with a phased rollout running throughout 2025