Black Hat Asia 2026 | Exploiting Message Queue Flaws in AI Inference Servers for Widespread RCE

AI inference servers have become critical infrastructure for deploying large language models at scale, with platforms like vLLM, SGLang, TensorRT-LLM, and others processing millions of enterprise AI workloads daily. These systems rely on inter-process communication channels to coordinate distributed model inference across GPU clusters, but we discovered that the standard architectural patterns used across the industry contain fundamental security flaws. We identified multiple Remote Code Execution vulnerabilities in the message queue implementations used by all major open-source AI inference platforms, affecting deployments from Meta, NVIDIA, Microsoft, and the PyTorch ecosystem. Through our internet-wide scanning, we confirmed thousands of vulnerable instances are directly exposed online, creating an attacker-accessible pathway into AI infrastructure at organizations worldwide. The vulnerabilities stem from dangerous code reuse patterns where insecure "reference implementations" were copied across projects, propagating the same logical flaws throughout the AI supply chain. In this Briefing, we will reveal the complete technical details and working exploits for these RCE vulnerabilities, demonstrate attacks against multiple platforms, and share our complex coordinated disclosure process across numerous vendors. We'll show how attackers can gain code execution on AI servers, potentially stealing models worth millions in training costs, poisoning inference results, or pivoting into broader enterprise networks. This research exposes critical lessons about security versus performance trade-offs in AI systems and the unique risks of rapid open-source code sharing in the AI community. Avi Lumelsky | Senior AI Researcher, Oligo Security Uri Katz | Senior Vulnerability Researcher, Oligo Security Gal Elbaz | CTO and Co-Founder, Oligo Security https://ift.tt/mRYtoTX

source https://www.youtube.com/watch?v=R7RWtcN5rAY

Black Hat Asia 2026 | Qualcomm BootROM: A Journey Through Sahara

BootROM is a critical component in the security architecture of many system-on-chips (SoCs), including the Qualcomm Snapdragon and MSM/MDM-family SoCs, deployed in billions of smartphones and IoT devices worldwide. As an embedded, immutable component, BootROM serves as the root of trust for the entire Secure Boot chain. This Briefing will present a comprehensive analysis of new vulnerabilities found by our team at the BootROM level: vulnerabilities in Emergency Download Mode (EDL) and its Sahara protocol, which allow bypassing cryptographic verification of Secondary Boot Loader (SBL) images and subsequent boot stages. The Briefing will demonstrate that functional vulnerabilities in EDL mode allow an attacker with physical access to the device to gain complete control of the modem subsystem and its QuRT operating system. Alexander Kozlov | Principal Security Researcher, Kaspersky Lab Sergey Anufrienko | Security Research Group Manager, Kaspersky Lab https://ift.tt/GT6lNwY

source https://www.youtube.com/watch?v=ZlWvdRBuxpc

Black Hat Asia 2026 | When Office Attacks: XLL Chains and Enterprise EDR Nightmares

Threat actors using malicious macros and XLLs as an attack vector is a tale as old as time. EDR and AV products developed to mitigate this are now well-equipped to stop malicious Microsoft Office macros, right? Turns out, not necessarily! Three years and countless malware infections later, we'll demonstrate how attackers continue to innovate, finding new ways to weaponize Office macros and XLL files to establish footholds in protected environments. As a red teamer, I spend an abundance of time doing security R&D to identify unique ways to break in, hide or break out of systems. The outcome of one such research cycle this year was a Frankenstein's monster of payloads, created using well-documented techniques and tactics to gain a foothold in a Windows system and bypass enterprise-level EDR detections. By combining Excel XLLs and Word macros, I created an attack chain that exploits the implicit trust organizations placed in legitimate business workflows. In this talk, I will dissect my custom initial access payload that chains macros and XLLs in unexpected ways with several sophisticated evasion techniques. We will explore the inner workings of Excel add-ins, COM automation, and process relationships that enable this technique to evade current popular EDR solutions. More importantly, we will examine why enterprise EDR deployments struggle with detection when operating at scale. Both offensive and defensive practitioners will gain valuable insights from this research. Red teamers will understand how legitimate business tools can be leveraged for initial access, while defenders will learn critical detection engineering strategies and incident response techniques. We will explore practical methods to identify, investigate and respond to such exploits and monitoring strategies, including a key configuration in a top EDR solution to detect this attack chain. This Briefing bridges the gap between offensive research and enterprise defense, providing actionable intelligence for organizations looking to strengthen their security posture against sophisticated macro-based attacks. Thanmayee Rao | Senior Red Team Engineer, Amazon https://ift.tt/JnfEKi4

source https://www.youtube.com/watch?v=RVAya4SoVBU

Black Hat Asia 2026 | IDEsaster 2.0: Another Novel Vulnerability Class in AI IDEs

AI IDEs continue to be on the rise, and they are not going away anytime soon. Last year, alongside dozens of vulnerabilities published publicly in AI IDEs, I published "IDEsaster" exposing a novel vulnerability class using AI agents and IDE features, leading to over 20 CVEs. This follow‑up research demonstrates that the architectural risks go deeper than previously understood. This Briefing presents (once again) a new universal vulnerability class affecting all AI IDEs. Unlike the previous attack chain, this one targets an underlying component that all of you use. A component not originally designed with the Secure for AI principle in mind, yet it strongly affects how IDEs behave. When AI agents interact with this component, it creates a powerful and largely invisible attack surface leading to an IDEsaster. The session concludes with higher‑level architectural insights on how AI applications need to be built to avoid this repeating issue. Ari (MaccariTA) Marzouk | Senior Security Researcher, Microsoft Red Team https://ift.tt/41IBs2u

source https://www.youtube.com/watch?v=uiIy9xUWGqU

Black Hat Asia 2026 | AirSnitch: Breaking Client Isolation in Wi-Fi Networks

We will present AirSnitch, a set of attacks that bypass Wi-Fi client isolation in home and enterprise Wi-Fi networks, enabling untrusted clients to attack others despite the usage of client isolation. Our attacks bypass Wi-Fi encryption and are effective even against modern WPA2/3 networks. Sometimes also called AP isolation, client isolation is not a standardized feature of Wi-Fi. Instead, vendors added it as an ad-hoc defense to prevent clients from attacking each other. For instance, client isolation prevents traditional ARP-based MitM attacks. However, we find that it is often implemented in inconsistent and insecure ways. We will present three main attack techniques to bypass client isolation. First, an adversary can abuse shared group keys to inject arbitrary traffic to a victim. Second, client isolation is often only implemented at the Ethernet layer, enabling bypasses at the IP layer. Third, an adversary can manipulate the forwarding tables of internal switches and bridges to intercept traffic despite the usage of client isolation. All combined, this enables us to restore MitM capabilities even in the face of client isolation. We find that most home routers are vulnerable, confirm vulnerabilities in real-world enterprise networks, and find that major operating systems such as Android, macOS, iOS, Windows, and Linux are affected. Mathy Vanhoef | Professor, KU Leuven University Zhiyun Qian | Professor, University of California, Riverside Xin'an Zhou | PhD Student, University of California, Riverside Juefei Pu | PhD Student, University of California, Riverside Zhutian Liu | PhD Student, University of California, Riverside Zhaowei Tan | Professor, University of California, Riverside Srikanth Krishnamurthy | Professor, University of California, Riverside https://ift.tt/ohtpIEV

source https://www.youtube.com/watch?v=1nevVb8ynsA

Black Hat Asia 2026 | Systematic Algorithmic Brute-Force Attacks Against UDS Security Access

The Unified Diagnostic Services (UDS) protocol—often referred to as the "HTTP of automotive ECUs"—relies on Service 0x27, "Security Access," to safeguard safety-critical operations, such as firmware reflashing, VIN rewriting, or ADAS calibration. Prior research has predominantly focused on firmware reverse-engineering, fault injection, or brute-forcing the key. However, with the widespread adoption of encrypted JTAG, hardened hardware, and secure supply-chain governance, these avenues are increasingly obstructed, rendering successful attacks rare and prohibitively expensive. We therefore introduce an algorithmic brute-force paradigm that reconstructs the algorithmic structure embedded within the ECU. Through three real-world case studies, AlgoBuster's battlefield performance is demonstrated. The framework has been tested on 12 ECUs launched after 2018 (covering nine Tier-1 suppliers), two of which were successfully broken. Jianwen Ren | ETAS Cybersecurity Consultant | Security MM Team Member, ETAS Jianchi Jiang | Automotive Security Engineer |Security MM Team Member, SGS Brightsight Su Shengfeng | Vehicle Security Engineer | Security MM Team Member, Ford Motor Company Lin Zengda | Security Researcher, Chen Guannan | OSR Security Researcher | Security MM Team Member, https://ift.tt/BpWOTFx

source https://www.youtube.com/watch?v=1RFx_5p3DYY

Black Hat Asia 2026 | IntentGuard: Securing LLM-Generated Cloud Configurations

GenAI assistants increasingly generate and modify configuration files—Kubernetes manifests, Terraform configurations, AWS CloudFormation templates, Helm charts, and others. These artifacts are security-critical, yet modern scanners and linters evaluate only correctness against predefined rules, not the operational intent the configuration is supposed to enforce. This creates a new attack surface: adversaries can poison configuration templates (via model jailbreaking or prompt injection), so that natural-language cues silently steer LLMs toward producing insecure configurations that still appear functionally correct. These "semantic misalignments" evade IaC scanning and pass human review because the generated configuration looks plausible but no longer matches the intended project purpose and security posture. This talk introduces IntentGuard, a novel Intent-Aligned Semantic Validation defensive framework that infers the intended behavior of a project, including configuration templates and marks configurations that contradict that intent. By reconstructing the service's intended role in the project—capturing its business, operational and performace roles, permitted communication graphs, dataflow and dependencies, privilege boundaries, —the framework identifies when configurations violate those structural and semantic intentions, enabling detection of latent misconfigurations such as conditional privilege escalation, unauthorized resource access, RBAC drift, information leakage, and infrastructure-level backdoors. Rather than relying on brittle prompt hardening or traditional scanners, intent-aligned validation detects when an LLM's output ceases to represent what the configuration was meant to enforce—even if the configuration is syntactically valid and operationally sound. Anna Bacher | CTO-Co-Founder, Jaroona GmbH Chris Wysopal | Co-Founder & Chief Security Evangelist, Veracode, Inc. https://ift.tt/GB2ASOY

source https://www.youtube.com/watch?v=Kd2eqp8ZUpA

Black Hat Asia 2026 | Faster Detection and Counteraction of N-Day Exploits in Chromium-based Apps

N-day exploitation speed is accelerating. For certain high-impact Chromium vulnerabilities, we observed exploitation attempts appearing shortly after public disclosure as fast as 24 hours, creating intense pressure on defenders. Yet many enterprise client applications built on Chromium face an asymmetric challenge: their release cadence and user-upgrade reality often lag behind attackers. Deep customization of the Chromium engine, fragmented client versions, and user groups that cannot readily update mean that official patches may take significant time to reach all endpoints. During this window, even well-managed products remain exposed. This talk presents a complementary, in-app defense architecture designed to operate alongside traditional patching, especially for applications where upgrading the underlying Chromium engine is slow or operationally difficult. Which integrates: • Accelerated patch analysis and down-version migration, enabling rapid internal adaptation of Chromium fixes across heterogeneous client baselines. • How to build an AI-based behavior-driven, in-app runtime detection capable of identifying exploitation attempts for newly disclosed CVEs across multiple client versions. • Realtime, on-client counteraction mechanisms that can disrupt or neutralize exploitation attempts, providing protection before a patched release can reach to the entire user base. This approach shortens the exposure window by adding a runtime, version-agnostic defense layer that can immediately respond to emerging threats. We will demonstrate how enterprises can enhance Chromium-based products with a layered, resilient protection model to reduce the operational risks posed by fast-moving N-day exploitation. Wenxiang Qian | Security Engineer Zhixin Tu | Security Engineer https://ift.tt/ClH5Gqe

source https://www.youtube.com/watch?v=-xaIpNlecJM

Black Hat Asia 2026 | Tropic Trooper Reloaded: Unraveling the Invisible Supply Chain Mystery

Tropic Trooper (a.k.a. Pirate Panda, KeyBoy) has long been known for its rapid adoption of emerging techniques and its willingness to deploy them aggressively in real-world intrusions. The group has repeatedly demonstrated a readiness to test unconventional intrusion vectors, such as deploying fake Wi-Fi access points in targeted physical areas. In past campaigns, we have also observed the adoption of post-exploitation techniques, such as abusing VS Code Remote Tunnels, as well as loader families engineered to resist analysis, including heavily obfuscated Xiangoop loader variants. The Xiangoop loader is a distinctive malware family associated with this threat actor. Based on our 2025 investigation, several new malware families, toolsets, and notable artifacts, including decoys were identified, providing fresh insight into the group's expanding geographic footprint and targeted industries. Recent activity has revealed a marked shift toward OSS-based tools within the infection chain. These findings highlight a rapid change in the actor's tooling strategy, demonstrating its ability to pivot quickly and overhaul their methods within a short period of time. Earlier activity in 2024 included a supply-chain compromise in which malware was delivered through what appeared to be the legitimate update process of a widely used dictionary application. Although the exact infection path was unclear at the time, a follow-up investigation in 2025 indicated that unauthorized changes had been made to the target's home router, resulting in malware infections. This session will provide a detailed overview of Tropic Trooper's operations in 2025, including the evolution of its loader and RAT ecosystem, abuse of home routers, and intrusion workflows. These findings reinforce the need for flexible, assumption-free investigative approaches, as this actor continues to shift techniques at high velocity. Suguru Ishimaru | Executive Cybersecurity Researcher, ITOCHU Cyber & Intelligence Inc. Satoshi Kamekawa | Cybersecurity Researcher, ITOCHU Cyber & Intelligence Inc. https://ift.tt/Dn8uUFN

source https://www.youtube.com/watch?v=8kXXc1Lsry0

Black Hat Asia 2026 | Advanced Glitching Leveraging Hidden CPU–eMMC Behavior

Secure Boot is a core security mechanism in embedded and automotive-grade SoCs, ensuring the integrity of the boot chain by verifying firmware signatures. However, in practical attacks, although fault injection techniques (such as EMFI and voltage glitching) are highly destructive, their success rate is fundamentally limited by the inability to precisely locate the moment when signature verification is performed. As a result, attackers are forced to blindly inject faults over hundreds of milliseconds of the boot process, leading to high noise, low success rates, and a significant risk of irreversible CPU damage. This presentation proposes a new high-precision fault attack localization method. In environments where the CPU provides no serial output, we jointly analyze the micro-level electromagnetic emission characteristics of the CPU core and the low-level timing behavior of the eMMC and DDR buses. By constructing a cross-domain hardware signal correlation model, we accurately calibrate the actual time point at which Secure Boot executes its verification logic. Through multi-level sampling and signal correlation, we compress the fault attack window from the second scale down to the millisecond or even nanosecond scale, transforming traditional "blind glitching" into a repeatable and precisely targeted attack. We demonstrate the complete process of successfully bypassing Secure Boot on real embedded devices using this method and reveal the physical leakage paths that exist between the CPU and peripheral storage during runtime. This research has significant implications for hardware security evaluation and fault injection attack studies. Jie Fu | Head of SkyHunter, China Telecom Cyber Security Technology Co., Ltd. Qiang Qin | Security Researcher, China Telecom Cyber Security Technology Co., Ltd. Shaohua Zhang | Security Researcher, China Telecom Cyber Security Technology Co., Ltd. Chunmei Zhang | Researcher, China Telecom Yang Chen | Senior Binary Researcher, China Telecom Cyber Security Technology Co., Ltd. YuJie Lu | Security Researcher, China Telecom Cyber Security Technology Co., Ltd. WeiChao Zhou | Director of Waterdrop Laboratory, China Telecom Cyber Security Technology Co., Ltd. https://ift.tt/j8vuWfr

source https://www.youtube.com/watch?v=VBF5ID-3Ve4

Black Hat Asia 2026 | Lost in Normalization: From URL Quirks to Poisoning the Azure Supply Chain

We transformed a single, isolated container in Azure Container Instances (ACI) for GPU into a full tenant-isolation breach and a critical supply chain attack. This talk details the multi-stage exploit chain that broke a seemingly secure, multi-layered design. It all started with a misconfiguration that exposed a container image for a highly sensitive internal Kubernetes component, effectively handing us its source code. We will demonstrate how we chained two novel vulnerabilities, discovered in this internal code, with advanced Kubernetes techniques to achieve critical service compromise. First, we achieved full cross-tenant credential theft, allowing us to steal secrets from other tenants' private container registries. More critically, we escalated this access to gain write permissions to a shared, production container registry used by ACI itself. This would have potentially allowed an attacker to poison trusted, official ACI images, creating a platform-wide supply chain attack. Shortly after, following the disclosure of these critical vulnerabilities, the service was retired. This Briefing serves as a case study in how a single flaw can undermine a robust security design. Attendees will get a rare look into the internal security architecture of a major cloud service and learn to identify and defend against similar platform-wide vulnerabilities. Nir Ohfeld | Head of Vulnerability Research, Wiz Ronen Shustin | Security Researcher, Wiz https://ift.tt/cUuI8hz

source https://www.youtube.com/watch?v=CdOw22fA6Xo