Security bugs often slip past static analysis not because they are impossible to detect, but because detection rules have not yet been written for the code in front of us. New frameworks, APIs, and coding idioms continually create such gaps, leaving developers to discover failures and manually encode new rules. We pres...
Me-Lo Rui, André V. Duarte, Aditya Oke et al.· 0 citations
Broken access control, the failure of authorization, is one of the most prevalent web security risks. Unlike injection, a flow of untrusted input into a dangerous operation, authorization is a relation: who may act on what, not how data moves. Each application decides that relation for itself, so no rule written in adv...
André V. Duarte, Aditya Oke, Me-Lo Rui et al.· 0 citations
This work proposes DRACO: Distributing Rubric-based Advantage for Credit Optimization, which generates rubrics dynamically during training to track the policy's evolving capability, scores those rubrics once per completed trajectory, and redistributes that judgment over the steps responsible for annotated rubrics to pr...
Shubham Gandhi, Saurabh Goyal, K. Kate et al.· 5 citations
A separate critic model that is specialized in high-level planning to steer the coding agent in inference and reduce the total inference costs for some coding agents by solving tasks in fewer steps is trained.