LeituraPesquisaRadarFramework de investimento
Entrar / Cadastrar
← Voltar para a leitura
NotíciasTópico · 思科AI审计证据框架Material3 min de leituraEditorial DisconfirmAI

Cisco's Al Chen: AI in Banking, Changing Version Numbers, Running Backups, and Hiding the Interface Is Not Enough

Al Chen, head of Cisco's AI Observability Software team, shared at the AI Engineer conference that bank security reviews do not seek a 'task completed' status, but rather checkable evidence for the correctness of every step. He used three examples—CVE remediation, cross-region disaster recovery, and LLM judge leakage—to illustrate the same principle: passing an explicit check does not mean the problem does not exist; additional verification is required.

2026-10-20 17:00 GMT+8

At the AI Engineer conference in October 2026, Al Chen, head of Cisco's AI Observability Software team, drew an analogy: his tenth-grade math teacher, Mr. Huff, required answers to be precise to the fourth decimal place, but most of the credit came from the proof process. Bank security and compliance teams are like Mr. Huff, except they hold multi-million-dollar compliance budgets. Chen's team deployed AI observability software into some of the world's largest banks, where they found that the real lever for shortening review cycles is not making models stronger, but ensuring every step can be inspected.

Take CVE remediation as an example. A platform has multiple images, each containing multiple CVEs, with different banks running different versions, using different scanning tools, and having their own severity policies and remediation deadlines. The conventional approach is to upgrade package versions or rebuild base Docker images, after which scanning tools (such as Sysdig, Wiz, Prisma, etc.) confirm the version change and release it. Chen points out this is far from enough: a changed version number does not mean that specific vulnerability cannot still be exploited in the application code. His team built additional evidence using the Harbor task framework—having agents write exploits based on the old version, attempt them on the new version, and then write tests to verify if the exploit still succeeds. Harbor can run multiple containers or sandboxes in parallel, providing multiple trials. Chen also acknowledged the boundary: a failed attempt is evidence regarding that specific exploit, not proof that all possible exploits are absent.

Entrar / Cadastrar
LeituraPesquisaRadarFramework de investimento

Disaster recovery follows the same pattern. Chen described a ClickHouse deployment where banks must arrange cross-region recovery themselves, as the platform lacks managed cross-region failover services. They use the open-source project clickhouse-backup to back up the primary region database to a storage bucket, then execute restore tasks in the disaster recovery region. Tool logs can show whether the task completed, but Chen says this status does not indicate whether the data is currently correct—bad disks, node failures, migration issues, or replication lag could cause data to be inconsistent with when the task was executed. He added table row count checks and intra-region replica convergence checks, shifting the verification object from 'did the task run' to 'is the data correct'.

The third example is the easiest to overlook. Desensitization processing at the SDK, gateway, or middleware layer makes the user-facing interface look clean, but LLM-as-a-judge creates another leakage path: the judge scores the agent's output and generates explanations for human review. If the judge sees raw traces, its reasoning process may reproduce personally identifiable information (PII) or material nonpublic information (MNPI). Chen suggested checking judge prompts and traces for leakage, and proposed a separation scheme: scores are always persisted for evaluation, while reasoning undergoes sensitive information checks before being displayed; if the bank still needs explanations, a second judge is run on desensitized input. The cost is one additional LLM call per request.

Chen's conclusion is that compliance speed depends on the bank's own readiness—whether there is already a process for pulling images from the registry, whether GPUs are in place, and whether security reviews and access configurations are ready. These delays stem more from organizational alignment than technology. His team treats customer problems as their own, categorizing them into engineering, process, and personnel organization lines, automating as much as possible.

Noteworthy boundaries: Chen describes scenarios where large vendors deploy the same product across multiple banks, and their engineering investment (maintaining the Harbor test framework, running dual judges, tracking open-source upstream dependencies) may not be directly transferable to small teams or single-customer deployments. The 'shortened from a year to a few weeks' he mentioned is relative; actual time still depends on the maturity of the bank's infrastructure and approval processes.

Fontes

  • youtube.com↗
Tópico

思科AI审计证据框架

思科正在通过“证据优先”策略重塑企业级AI的信任机制。其核心逻辑在于:传统的版本升级或静态扫描不足以证明AI系统的安全性,必须提供可验证的运行时证据。在银行场景下,思科团队利用Harbor任务让AI代理编写并执行攻击代码以验证漏洞修复,并通…

3 etapas1 peçasAtualizado 2026-10-27 18:04

Como chegamos aqui

  1. 2026-10-20思科博客宣布与Workday合作,Cisco AI Defense作为Workday Agent Passport的启动评估方,为AI代理提供基于OWASP/NIST标准的对抗性测试和安全印章。blogs.cisco.com ↗
  2. 2026-10-23Sean Weldon发布分析文章,详细拆解思科Al Chen提出的银行AI部署三支柱框架:构建管道/CVE修复、数据弹性/灾备、PII/MNPI泄露预防,强调证据而非声明决定部署速度。sean-weldon.com ↗
  3. 2026-10-27思科AI可观测性软件团队负责人Al Chen在AI Engineer大会发表演讲,具体阐述如何利用Harbor任务自动化验证CVE修复有效性,以及ClickHouse跨区灾备中的行级正确性检查。youtube.com ↗

O que ainda está indefinido

  • 思科DefenseClaw开源工具与商业版AI Defense在银行等强监管环境下的功能边界与合规认证差异是什么?
  • Workday Agent Passport的安全印章是否会被其他金融机构或监管机构直接认可,还是需要二次审计?
  • 在依赖上游开源维护者修复CVE的情况下,思科的“解释性报告”能否真正满足银行对零日漏洞的SLA要求?
Ler o tópico completo →
Continuar pesquisando →