🚀 Open-weight LLMs offer huge potential but also new cyber risks. Once weights are public, the "genie is out of the bottle." My paper explores policy gaps (like in the EU AI Act) & proposes how to mitigate these risks without stifling innovation.
arxiv.org/abs/2505.17109
#OffensiveAI #Cybersecurity
arxiv.org/abs/2505.17109
#OffensiveAI #Cybersecurity
Mitigating Cyber Risk in the Age of Open-Weight LLMs: Policy Gaps and Technical Realities
Open-weight general-purpose AI (GPAI) models offer significant benefits but also introduce substantial cybersecurity risks, as demonstrated by the offensive capabilities of models like DeepSeek-R1 in ...
arxiv.org
May 27, 2025 at 1:37 PM
🚀 Open-weight LLMs offer huge potential but also new cyber risks. Once weights are public, the "genie is out of the bottle." My paper explores policy gaps (like in the EU AI Act) & proposes how to mitigate these risks without stifling innovation.
arxiv.org/abs/2505.17109
#OffensiveAI #Cybersecurity
arxiv.org/abs/2505.17109
#OffensiveAI #Cybersecurity
Headed to RSA? Come meet the Dreadnode crew!
Whether you're looking for a private deep dive into our tech or want to hang out and talk offensive AI research, we'd love to connect.
Limited availability; Come and get it: calendly.com/tori-dreadno...
#BayArea #SanFrancisco #RSAC2025 #OffensiveAI
Whether you're looking for a private deep dive into our tech or want to hang out and talk offensive AI research, we'd love to connect.
Limited availability; Come and get it: calendly.com/tori-dreadno...
#BayArea #SanFrancisco #RSAC2025 #OffensiveAI
April 16, 2025 at 4:12 PM
Headed to RSA? Come meet the Dreadnode crew!
Whether you're looking for a private deep dive into our tech or want to hang out and talk offensive AI research, we'd love to connect.
Limited availability; Come and get it: calendly.com/tori-dreadno...
#BayArea #SanFrancisco #RSAC2025 #OffensiveAI
Whether you're looking for a private deep dive into our tech or want to hang out and talk offensive AI research, we'd love to connect.
Limited availability; Come and get it: calendly.com/tori-dreadno...
#BayArea #SanFrancisco #RSAC2025 #OffensiveAI
Good policy is grounded in technical reality. Bad policy creates loopholes – Or, how my input informed the updated GPAI Code of Practice of the EU AI Act.
#TechPolicy #AIGovernance #EUAIAct #OffensiveAI
www.linkedin.com/feed/update/...
#TechPolicy #AIGovernance #EUAIAct #OffensiveAI
www.linkedin.com/feed/update/...
#techpolicy #aigovernance #euaiact #standardization #cybersecurity #ai #aisecurity #cybersecmonth | Alfonso De Gregorio
Good policy is grounded in technical reality. Bad policy creates loopholes.
In my last post, I discussed the "mitigation gap" with open-weight AI. A critical question arose from this: If a developer ...
www.linkedin.com
October 25, 2025 at 6:33 AM
Good policy is grounded in technical reality. Bad policy creates loopholes – Or, how my input informed the updated GPAI Code of Practice of the EU AI Act.
#TechPolicy #AIGovernance #EUAIAct #OffensiveAI
www.linkedin.com/feed/update/...
#TechPolicy #AIGovernance #EUAIAct #OffensiveAI
www.linkedin.com/feed/update/...
From shaping AI policy to building the technical standards that bring it to life.
linkedin.com/feed/update/...
#ETSI #AIstandards #TechPolicy #AIGovernance #OffensiveAI
linkedin.com/feed/update/...
#ETSI #AIstandards #TechPolicy #AIGovernance #OffensiveAI
#etsi #aistandards #standardization #techpolicy #aigovernance #cybersecurity #aisecurity #offensiveai #euaiact #aiact | Alfonso De Gregorio
From shaping AI policy to building the technical standards that bring it to life.
Following the discussions on my work influencing the EU AI Act's GPAI Code of Practice, I have some exciting news to ...
linkedin.com
October 28, 2025 at 10:53 AM
From shaping AI policy to building the technical standards that bring it to life.
linkedin.com/feed/update/...
#ETSI #AIstandards #TechPolicy #AIGovernance #OffensiveAI
linkedin.com/feed/update/...
#ETSI #AIstandards #TechPolicy #AIGovernance #OffensiveAI