Die Gefahr lauert in der KI
#Cybersecurity #Cybersicherheit #Jailbreak #künstlicheIntelligenz #LLM #LLMSalting @Sophos #SophosAI #Sprachmodell @Sophos_Info
netzpalaver.de/2025/...
#Cybersecurity #Cybersicherheit #Jailbreak #künstlicheIntelligenz #LLM #LLMSalting @Sophos #SophosAI #Sprachmodell @Sophos_Info
netzpalaver.de/2025/...
November 4, 2025 at 12:37 PM
Die Gefahr lauert in der KI
#Cybersecurity #Cybersicherheit #Jailbreak #künstlicheIntelligenz #LLM #LLMSalting @Sophos #SophosAI #Sprachmodell @Sophos_Info
netzpalaver.de/2025/...
#Cybersecurity #Cybersicherheit #Jailbreak #künstlicheIntelligenz #LLM #LLMSalting @Sophos #SophosAI #Sprachmodell @Sophos_Info
netzpalaver.de/2025/...
At the Conference for Applied Machine Learning in Information Security (CAMLIS) yesterday, SophosAI researcher Tamás Vörös presented his research on LLM salting, a novel technique to prevent LLM jailbreaks.
Many organizations are increasingly deploying LLMs with minimal customization. This […]
Many organizations are increasingly deploying LLMs with minimal customization. This […]
Original post on infosec.exchange
infosec.exchange
October 24, 2025 at 10:24 AM
At the Conference for Applied Machine Learning in Information Security (CAMLIS) yesterday, SophosAI researcher Tamás Vörös presented his research on LLM salting, a novel technique to prevent LLM jailbreaks.
Many organizations are increasingly deploying LLMs with minimal customization. This […]
Many organizations are increasingly deploying LLMs with minimal customization. This […]
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
Interest | Match | Feed
Interest | Match | Feed
Origin
news.sophos.com
October 21, 2025 at 10:58 AM
Getting salty with LLMs: SophosAI unveils new defense against jailbreaking at CAMLIS 2025
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
news.sophos.com
October 21, 2025 at 10:31 AM
Getting salty with LLMs: SophosAI unveils new defense against jailbreaking at CAMLIS 2025
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 jailb...
#Malware #News
Origin | Interest | Match
#Malware #News
Origin | Interest | Match
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 Introduction to Malware Binary Triage (IMBT) Course Looking to level up your skills? Get 10% off using coupon code: MWNEWS10 for any flavor. Enroll Now and Save 10%: Coupon Code MWNEWS10 Note: Affiliate link – your enrollment helps support this platform at no extra cost to you. Article Link: Getting salty with LLMs: SophosAI unveils ne...
malware.news
October 21, 2025 at 11:01 AM
Getting salty with LLMs: SophosAI unveils new defense against jailbreaking at CAMLIS 2025 news.sophos.com/en-us/2025/1...
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
news.sophos.com
October 21, 2025 at 10:29 AM
Getting salty with LLMs: SophosAI unveils new defense against jailbreaking at CAMLIS 2025 news.sophos.com/en-us/2025/1...
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 jailb...
#AI #Research #AI #CAMLIS #featured #LLM #Sophos #X-Ops
Origin | Interest | Match
#AI #Research #AI #CAMLIS #featured #LLM #Sophos #X-Ops
Origin | Interest | Match
October 21, 2025 at 11:00 AM
SophosAI at Black Hat USA ’25: Anomaly detection betrayed us, so we gave it a new job Sophos’ Ben Gelman and Sean Bergeron will present their research on enhancing command line classification with benign anomalous data at Las Vegas
Interest | Match | Feed
Interest | Match | Feed
Origin
news.sophos.com
July 14, 2025 at 12:19 PM
SophosAI at Black Hat USA ’25: Anomaly detection betrayed us, so we gave it a new job
SophosAI at Black Hat USA ’25: Anomaly detection betrayed us, so we gave it a new job
Sophos’ Ben Gelman and Sean Bergeron will present their research on enhancing command line classification with benign anomalous data at Las Vegas
news.sophos.com
July 14, 2025 at 10:41 AM
SophosAI at Black Hat USA ’25: Anomaly detection betrayed us, so we gave it a new job
SophosAI at Black Hat USA ’25: Anomaly detection betrayed us, so we gave it a new job Sophos’ Ben Gelman and Sean Bergeron will present their research on enhancing command line classification w...
#Threat #Research #anomaly #detection #black #hat #2025 […]
[Original post on news.sophos.com]
#Threat #Research #anomaly #detection #black #hat #2025 […]
[Original post on news.sophos.com]
July 14, 2025 at 12:19 PM
SophosAI at Black Hat USA ’25: Anomaly detection betrayed us, so we gave it a new job Sophos’ Ben Gelman and Sean Bergeron will present their research on enhancing command line classification w...
#Threat #Research #anomaly #detection #black #hat #2025 […]
[Original post on news.sophos.com]
#Threat #Research #anomaly #detection #black #hat #2025 […]
[Original post on news.sophos.com]
SophosAI has released an open-source toolkit for training out-of-the-box Large Language Models on proprietary data to tune them for use in specific applications--like security operations center applications. The toolkit is based on Microsoft Research's DeepSpeed, and adapts it for easy […]
Original post on infosec.exchange
infosec.exchange
December 13, 2024 at 2:07 PM
SophosAI has released an open-source toolkit for training out-of-the-box Large Language Models on proprietary data to tune them for use in specific applications--like security operations center applications. The toolkit is based on Microsoft Research's DeepSpeed, and adapts it for easy […]
My colleagues over in SophosAI have done an experiment to see how easy it would be to create an automated generative AI political disinformation machine.
TLDR: It's too easy.
news.sophos.com/en-us/2024/1...
TLDR: It's too easy.
news.sophos.com/en-us/2024/1...
Political Manipulation with Massive AI Model-driven Misinformation and Microtargeting
Applying generative AI, bad actors could tailor disinformation campaigns to affect election outcomes on a massive scale with relatively little effort.
news.sophos.com
October 2, 2024 at 8:18 PM
My colleagues over in SophosAI have done an experiment to see how easy it would be to create an automated generative AI political disinformation machine.
TLDR: It's too easy.
news.sophos.com/en-us/2024/1...
TLDR: It's too easy.
news.sophos.com/en-us/2024/1...