REVA：用单次前向传播实现实时漏洞检测
Reva: Real-Time Vulnerability Detection through Contextual Probing of Large Language Models
Agent 查漏洞太慢，这篇论文直接读 LLM 内部表示，1 秒判定一个函数，比 agentic 方案快 250 倍还不掉准确率，做安全工具的可以看看。
论文提出 REVA，把安全上下文、静态分析结果和调用图信息一次性喂给 LLM，再用训练好的探针读取模型内部表示来判断漏洞。在 PrimeVul 测试集上，REVA 基于 GLM-5.3-Flash 达到 60.0% 准确率，每个函数约 1 秒。这与 agentic 检测器 VulTriage 的 59.2% 准确率相当，但速度快 250 倍以上、成本不到其十分之一。同一提示词下，探针比 LLM 直接给出的结论准确率高 14% 到 17%。
Reva: Real-Time Vulnerability Detection through Contextual Probing of Large Language Models
A vulnerability costs more to fix the later it is discovered. As coding agents generate code faster than developers can review it, software needs a first line of defense screening each new function in real time. LLM agents have recently become capable of finding real-world vulnerabilities by working as a security expert would: they run analysis tools, explore the surrounding code, test hypotheses and weigh the evidence before forming their own judgement. This reasoning, however, spans many model calls, so that each verdict takes minutes of compute, far too long for real-time screening. Faster detectors, which fine-tune deep learning models or prompt an LLM for a direct verdict, are less accurate: they judge a function without the context an agent gathers, and an LLM's generated verdict is unreliable even when given some of it. We present REVA (REal-time Vulnerability Analysis), an AI vulnerability detector that brings the security context and code understanding components behind agentic detectors into a single forward pass of an LLM. For each new function, REVA gives the LLM a pre-computed threat model of its module, lightweight static analysis findings and call-graph information. REVA leverages a trained probe to read the LLM's internal representations of the new function in this context. On PrimeVul's held-out test set, REVA on GLM-5.3-Flash reaches 60.0% accuracy in about one second per function. This matches VulTriage (59.2%), the state-of-the-art agentic detector, run on the same LLM, while being over 250 times faster and less than a tenth as costly. On the same prompt, the probe is 14% to 17% more accurate than the LLM's own direct verdict. Across three open LLMs, REVA is at least as accurate as VulTriage, and about 10% more accurate on two of them. An LLM's internal representations thus encode much of what agentic detectors obtain through reasoning.