Latest news with #Jailbreak
Yahoo
23-05-2025
- Entertainment
- Yahoo
Classic Rock Guitarist, 74, Reveals He ‘Actually Died' During Recent Operation
The rock world nearly lost Thin Lizzy's Scott Gorham. Gorham, who joined Phil Lynott's band in 1974, is recuperating after nearly dying on the operating table. "I had a health issue scare about a year ago with a kidney that had to be removed, and I got sepsis from it," Gorham said on the May 21 episode of Darren Paltrowitz's Paltrocast podcast. "And the second surgeon said I actually died on the operating table and all that. And I was, like, 'Really, man? What the hell is all that about?'" Though Gorham wasn't a founding member, he's considered an essential part of Thin Lizzy. He was one of the band's "twin lead guitarists" and Scott played on albums like Nightlife, Fighting and Jailbreak (which featured the band's biggest U.S. hit, "The Boys Are Back In Town"). Gorham reformed Thin Lizzy in 1996, 13 years after the band broke up and a decade after Lynott's death. He also played in the Thin Lizzy spin-off band, Black Star Riders, before departing in 2021 to focus strictly on Thin Lizzy. In November, Gorham discussed putting together "just an absolute kick-[explicative] Thin Lizzy band" together for a tour, but he told Paltrocast that he's not ready to get back on the road. "And now I had a third operation, and [my doctor] said, 'Maybe you should take some time out and just kind of rehabilitate and all that, get your strength back and all that.' So that's what I'm doing," said Gorham. "And in the meantime, I've got the drawing to keep me occupied," he said. Last year, Gorham revealed his secret passion as an artist and held his first art exhibition in London. "[Drawing] is the new thing for me," said Gorham. "It's something that I thought I'd never really do as a constant thing. So I'm kind of enjoying this kind of break from the music right now and going into this little bit of a different direction." This doesn't mean his music career is over. Scott said that he hopes to "get my buns back out on the road" sometime Rock Guitarist, 74, Reveals He 'Actually Died' During Recent Operation first appeared on Parade on May 23, 2025
TECHx
11-03-2025
- Business
- TECHx
Qualys Flags DeepSeek-R1 LLaMA Model Vulnerabilities
Qualys recently conducted a security analysis of the DeepSeek-R1 LLaMA 8B model using its new AI security platform, Qualys TotalAI, revealing concerning vulnerabilities. The analysis found that the DeepSeek model had a failure rate of 61% when tested against Qualys TotalAI's Knowledge Base (KB) attacks and 58% against Jailbreak attacks, highlighting significant security risks. The KB analysis by Qualys TotalAI evaluates responses from the model across 16 categories such as controversial topics, factual inconsistencies, hate speech, legal concerns, privacy attacks, and sensitive information disclosure. The model failed 61% of 891 tests, with the lowest pass rates in misalignment (8%), controversial topics (13%), and factual inconsistencies (21%). However, the model excelled in filtering sexual content, passing 100% of the tests in that area. In the Jailbreak testing, DeepSeek-R1 LLaMA faced 885 attacks from 18 different jailbreak types, failing 58% of the time. These jailbreak attempts exposed serious security weaknesses, such as generating harmful content, including instructions on making explosive devices, promoting hate speech, and spreading false medical information. Jailbreaking bypasses safety mechanisms and allows the model to produce restricted responses, which can have dangerous consequences in enterprise and regulatory settings. Dilip Bachwani, CTO of Qualys, commented, 'As AI adoption accelerates, organizations must address security, safety, and compliance challenges. Gaining visibility into AI assets, assessing vulnerabilities, and proactively mitigating risks are critical to ensuring responsible and secure AI deployment.' Qualys TotalAI provides organizations with full visibility into AI workloads, helping to detect risks like prompt injections, jailbreaks, and ethical concerns such as bias and harmful language. This comprehensive AI security platform ensures that AI models remain secure, compliant, and resilient as organizations scale their deployments.
