Direct Preference Optimization (DPO) treats all constraint violations equally: a $1 budget overshoot and a $1,000 overshoot induce the same training signal. It is also susceptible to length and style bias when preference pairs come from different model families. We introduce Constraint-Margin DPO (CM-DPO), which replac...
SkillGuard is presented, a harness-level enforcement layer that treats this event as contamination and restricts future capabilities to disconnect the resulting state from deployer-defined forbidden states and preserves substantially more capabilities than binary restriction at the same attack success rate.
Wu-Jie Xiong, Rabimba Karanjai, Yang Lu et al.· 2 citations
PACE (Policy-Attested Contract Execution), a transaction-level authorization framework that interposes between an LLM-based agent and on-chain execution, is presented and frame its claims as logic-level safety within a reproducible benchmark rather than deployment-ready DeFi security.
Rabimba Karanjai, Yang Lu, Richard Williamson et al.· 1 citation
The results establish that LLM-based log analysis creates an inherent confused deputy vulnerability where untrusted data and trusted instructions compete indistinguishably for model attention, requiring defense in-depth architectures and continued human oversight for security-critical decisions.
Rabimba Karanjai, Yang Lu, H. Madhavarao et al.· 2 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
