Sophos AI to present on how to defang malicious AI models at Black Hat Europe
“LLMbotomy” research reveals how Trojans can be injected into Large Language Models, and how to disarm them.
Similar Posts
Inside the Mind of the Adversary: Why More Security Leaders Are Selecting AEV
Bys sCybersecurity involves both playing the good guy and the bad guy. Diving deep into advanced technologies and yet also going rogue in the Dark Web. Defining technical policies and also profiling attacker behavior. Security teams cannot be focused on just ticking boxes, they need to inhabit the attacker’s mindset. This is where AEV comes in….
React2Shell flaw (CVE-2025-55182) exploited for remote code execution
Bys sThe availability of exploit code will likely lead to more widespread opportunistic attacks Tags: Threat Research, Featured, vulnerability, react2shell
Data from Insight Hospital and Medical Center Leaked on Dark Web
Bys sOn or about January 26, 2026, Insight Hospital and Medical Center (“Insight”) in Chicago issued a substitute notice. It states that in September 2025, Insight learned of unusual activity within its network. An investigation subsequently determined that an unauthorized individual accessed the network between August 22, 2025 and September 11, 2025. As of the date……
Malicious PyPI Package Posing as Solana Tool Stole Source Code in 761 Downloads
Bys sCybersecurity researchers have discovered a malicious package on the Python Package Index (PyPI) repository that purports to be an application related to the Solana blockchain, but contains malicious functionality to steal source code and developer secrets. The package, named solana-token, is no longer available for download from PyPI, but not before it was downloaded 761…
At U.S. request, France jails Russian basketball player Daniil Kasatkin on suspicion of ransomware conspiracy
Bys sMeduza reports: A court in Paris has jailed Russian basketball player Daniil Kasatkin on suspicion of involvement in a hacker group’s extortion activities. The 26-year-old was arrested on June 21 at Charles de Gaulle airport at the request of the United States, which has charged him with conspiracy to commit computer fraud. According to American investigators, Kasatkin…
Microsoft Discloses DNS-Based ClickFix Attack Using Nslookup for Malware Staging
Bys sMicrosoft has disclosed details of a new version of the ClickFix social engineering tactic in which the attackers trick unsuspecting users into running commands that carry out a Domain Name System (DNS) lookup to retrieve the next-stage payload. Specifically, the attack relies on using the “nslookup” (short for nameserver lookup) command to execute a custom…