2 papers
cs.CR2026
Not All Refusals Are Equal: How Safety Alignment Fails Cybersecurity at Scale
Vadym Hadetskyi, Dario Pasquini, Artem Sorokin
There is no doubt that safety alignment is an essential step in LLM training. However, conceptually it does not distinguish between various domains and the level of potential harm…
cs.CR2026
Red-Teaming the Agentic Red-Team
Dario Pasquini, Michal Bazyli, Taras Fedynyshyn +1
The use of agentic systems to perform offensive security operations has moved from a theoretical possibility to a commoditized capability. However, while the community has focused…