Getting salty with LLMs: SophosAI unveils new defense against jailbreaking at CAMLIS 2025
On October 22-24, SophosAI will present research on ‘LLM salting’ (a novel countermeasure against jailbreaks) and command line classification at CAMLIS 2025
Similar Posts
CISA and FDA Warn of Critical Backdoor in Contec CMS8000 Patient Monitors
Bys sThe U.S. Cybersecurity and Infrastructure Security Agency (CISA) and the Food and Drug Administration (FDA) have issued alerts about the presence of hidden functionality in Contec CMS8000 patient monitors and Epsimed MN-120 patient monitors. The vulnerability, tracked as CVE-2025-0626, carries a CVSS v4 score of 7.7 on a scale of 10.0. The flaw, alongside two…
Researchers Expose SVG and PureRAT Phishing Threats Targeting Ukraine and Vietnam
Bys sA new campaign has been observed impersonating Ukrainian government agencies in phishing attacks to deliver CountLoader, which is then used to drop Amatera Stealer and PureMiner. “The phishing emails contain malicious Scalable Vector Graphics (SVG) files designed to trick recipients into opening harmful attachments,” Fortinet FortiGuard Labs researcher Yurren Wan said in a report shared…
Call for Presentations Open for SecurityWeek’s 2025 Supply Chain Security & Third-Party Risk Summit
Bys sJoin Us in Shaping the Future of Supply Chain Security – Don’t miss this chance to be part of the conversation addressing one of the most pressing cybersecurity challenges . The post Call for Presentations Open for SecurityWeek’s 2025 Supply Chain Security & Third-Party Risk Summit appeared first on SecurityWeek.
⚡ Weekly Recap: WhatsApp 0-Day, Docker Bug, Salesforce Breach, Fake CAPTCHAs, Spyware App & More
Bys sCybersecurity today is less about single attacks and more about chains of small weaknesses that connect into big risks. One overlooked update, one misused account, or one hidden tool in the wrong hands can be enough to open the door. The news this week shows how attackers are mixing methods—combining stolen access, unpatched software, and…
Malicious Browser Extensions Infect 722 Users Across Latin America Since Early 2025
Bys sCybersecurity researchers have shed light on a new campaign targeting Brazilian users since the start of 2025 to infect users with a malicious extension for Chromium-based web browsers and siphon user authentication data. “Some of the phishing emails were sent from the servers of compromised companies, increasing the chances of a successful attack,” Positive Technologies…
Meta Warns of FreeType Vulnerability (CVE-2025-27363) With Active Exploitation Risk
Bys sMeta has warned that a security vulnerability impacting the FreeType open-source font rendering library may have been exploited in the wild. The vulnerability has been assigned the CVE identifier CVE-2025-27363, and carries a CVSS score of 8.1, indicating high severity. Described as an out-of-bounds write flaw, it could be exploited to achieve remote code execution…