RESEARCH
Reports, datasets, market studies and original CyberCoverInsight research.
A large conference's proceedings inflate the counts, so the jumps should be read with caution. The content is strong on AI agents (hijacking Android GUI agents, defenses for LLM ones), on defeating memory protections (V8 sandbox, kernel MTE) and on side channels in cryptographic implementations and TEEs.
Nov 15, 2026
ReadThis week three studies test AI agents: poisoned MCP tools that succeed in almost one case in four, signed tools that leak data and Office files the model reads differently from us. On hardware, a Trojan in sensors and two attacks on SLH-DSA and ML-KEM stand out. Compiler bugs in zkVMs and browser NativeMessaging round out the edition.
Nov 08, 2026
ReadA week dominated by cryptography: post-quantum papers rise to 35, more than double the average, with hardware accelerators and parameter choices for ML-KEM and ML-DSA. Side channels keep targeting post-quantum implementations, cryptography for blockchains grows and AI security falls in volume. Attention emerges for compilers and sensors compromised before use.
Nov 08, 2026
ReadIn the third quarter of 2026 cyber insurance prices fell 4% globally, the same as the previous quarter, while US prices held flat. Europe fell 9%. With NAIC data on the US market, the AMRAE study on France and the questions to bring to renewals.
Nov 01, 2026
ReadAn estimate of Shor's algorithm on cat qubits puts RSA-2048 factoring at about 23,000 physical qubits and 3.14 days, under explicit hardware assumptions. On LLM agents, prompt injection works better hidden in README and TODO files, and role spoofing impersonates the user. The other papers measure the gap between tests and reality, from malware benchmarks to industrial detectors.
Oct 31, 2026
ReadCryptography dominates the week: 54 papers against an average of 23.2, and post-quantum rises to 26 against 7.5, with much work on implementing standardized schemes. The second thread is hardware getting around software: TPM 2.0, SLH-DSA and LLM inference. AI security falls in numbers but concentrates on agents. Single-week counts remain noisy.
Oct 25, 2026
ReadAI agents and models are a new risk surface: a secret deleted from an agent's memory is recovered from summaries and fragments, a cloud provider infers sensitive data from a manipulated model's latency, AgentTriage reconstructs what an agent did. The second thread is social engineering. On post-quantum, a critical reading of the attacks on Classic McEliece.
Oct 25, 2026
ReadHardware is undermining software guarantees: TPM 2.0 disk encryption falls on Windows and Linux, power analysis recovers the SLH-DSA seed, a single Rowhammer bit-flip slows LLM inference. The second thread is trust in critical systems, from Estonia's internet voting to backdoors in cipher designs. Also notable: prompt injections planted in forensic evidence.
Oct 24, 2026
ReadThis edition covers 1 to 23 October 2026; daily digests start on the 24th. An open model can hide in its weights a trojan that exfiltrates secrets over DNS, and persistent memory in AI assistants makes prompt injections last. Valid PDF signatures fool readers, small-satellite radio modules prove vulnerable and the European identity wallet gains protection against issuers.
Oct 23, 2026
ReadSeptember 2026 is CHES month: physical attacks recover keys from masked ML-KEM, Classic McEliece and even NIST's Hash-DRBG random generator. Smart glasses record passwords typed on phones, infostealer logs show 170,000 victims and shared compression exposes SSH channels. Agents run more than the user approves.
Sep 30, 2026
ReadIn August 2026 language models help find 31 zero-days in PDF readers and flaws in 5G cores and Ethereum clients. Encrypted reasoning returned by model APIs can be decrypted by a weaker model, and the shared cache on Apple chips lets the CPU spy on the GPU. A systematisation shows that moving TLS to post-quantum is an architecture problem.
Aug 31, 2026
ReadIn July 2026 a few leaked bits are enough to recover Falcon, HAWK and ML-DSA keys, and neural networks automate side-channel attacks on ML-KEM. Phones and browsers can be recognised from hundreds of properties or tiny GPU manufacturing differences. WeChat mini-apps get OAuth login wrong, and a rendering delay fools visual phishing detectors.
Jul 31, 2026
ReadIn June 2026 coding agent extensions become a new supply chain dependency, and current detectors see only part of the risk. Partial ROV deployment enables BGP hijacks the victim cannot see, AirDrop and Quick Share show zero-click flaws, and a study reconstructs how law enforcement breached Encrochat.
Jun 30, 2026
ReadMay 2026 is IEEE S&P month. With cheap hardware on the memory bus, two teams break Intel SGX, TDX and AMD SEV-SNP, and GPU Rowhammer leads all the way to system control. MCP tools combine into chains that exfiltrate data, and AI agent browsers bypass site isolation. OAuth, password managers and attack attribution round out the month.
May 31, 2026
ReadApril 2026 brings the IEEE S&P proceedings. Valid but inconsistent 5G messages crash the modems of 542 smartphone models, and imperceptible audio hijacks voice assistants. Computer-use agents cause harm even from benign instructions. On the post-quantum side, HQC and Falcon give way to side channels. The insurance lead market and the AI Act close the month.
Apr 30, 2026
ReadMarch 2026 is OpenClaw's month: the open-source framework for local agents proves fragile and AgentWorm spreads from one instance to the next with a single message. New estimates lower the quantum resources needed to break cryptocurrency keys. On hardware, Trojans invisible under the microscope, Falcon keys recovered by cold boot and models stolen from a GPU a metre away.
Mar 31, 2026
ReadFebruary 2026 puts the AI agent supply chain centre stage: third-party skills, bundles of instructions and scripts, carry malicious code and injections that agents follow up to 80% of the time. Agents can exfiltrate data while their answer looks harmless, and LLMs make online deanonymisation a mass operation. Android updates and passkeys round out the month.
Feb 28, 2026
ReadJanuary 2026 is NDSS month. Malware brings its own signed, vulnerable drivers to switch off defences, and an architecture like ACE separates agent planning from untrusted apps. A handful of neurons hold up LLM alignment, desktop password managers give way to simulated keystrokes and email aliases confuse identities. IoT firmware, PLCs and PyPI packages round out the month.
Jan 31, 2026
ReadDecember 2025 takes AI agents onto new ground: poisoned memories that persist across sessions, injections that work from any source and prompts that trap a service in endless reasoning. On the cryptographic side, Telegram and electric-vehicle plug-and-charge show concrete weaknesses. The month closes with virtual machine escapes and consent violations in web forms.
Dec 31, 2025
ReadNovember 2025 is dominated by the ACM CCS proceedings. Three attacks crack confidential computing, from AMD SEV-SNP to Intel SGX and Arm GPUs. Thousands of mobile apps ship working credentials, and indicators of compromise are often published after attackers have already moved on. The month also brings kernel bugs once deemed unexploitable and a windshield turned into a loudspeaker.
Nov 30, 2025
ReadOctober 2025 puts AI agents to the test: a benchmark measures twelve attacks through the Model Context Protocol, while quantization alone is enough to hide a backdoor in a model. Thirteen bytes send malware down the wrong path in Gmail's filter. The month also brings model signing on GPUs, LLMs against malicious npm updates and amplification through transparent DNS forwarders.
Oct 31, 2025
ReadSeptember 2025 opens with EchoLeak, the first zero-click prompt injection exploited in a production enterprise assistant. The ACM CCS proceedings also bring a defence for computer-use agents, a systematic look at ten years of APT campaigns, attacks on SSH client signatures and on k-anonymised clinical data, and off-path TCP hijacking over shared IP addresses.
Sep 30, 2025
ReadAugust 2025 questions some basic tools. CVSS, EPSS and other scoring systems rank the same vulnerabilities very differently, and AI model scanners miss most ways of poisoning them. Cloned-voice calls can be unmasked with listening challenges, and password strength meters reveal the passwords they were trained on.
Aug 31, 2025
ReadJuly 2025 brings Rowhammer to the GPUs used for AI, with model accuracy dropping by up to 80%. Downloaded models can hide self-extracting malware, email-handling agents fall to a new kind of prompt injection, and an AI agent writes profitable smart contract exploits. On mobile, WebViews and SDKs bypass protections and over half of sensitive apps ignore secure hardware.
Jul 31, 2025
ReadJune 2025 shifts the focus to the physical world. Ship officers report spoofed GPS and ransomware on board, CAN bus data rebuild a car's route without GPS, and a video of a 3D printer is enough to steal its design. Computer-use agents fall for instructions hidden in screens, and fuzzing finds ten CVEs in 5G modems.
Jun 30, 2025
ReadMay 2025 is IEEE S&P month and hardware is back at the centre. Rowhammer extracts Kyber, BIKE and Dilithium keys, brief physical tampering with RAM breaks AMD SEV-SNP's guarantees and Apple chips speculate on data never read. On AI, anti-deepfake watermarks can be erased. 38 of 43 password managers remain exposed to offline attacks on the master password.
May 31, 2025
ReadApril 2025 is the month of agents wired to external tools: MCP enables credential theft, a malicious document hijacks tool selection, and a new defence trains an LLM to spot prompt injection. Beyond AI, the XZ Utils backdoor is reconstructed step by step, AI-based weather forecasts can be faked, and post-quantum SSH gets its first full analysis.
Apr 30, 2025
ReadMarch 2025 brings the focus back to implementation. Kyber's reference code leaked the key through division timings, and five encrypted backup tools reveal content through their chunking. AI browser assistants send whole pages to their servers, Bluetooth and Wi-Fi SDKs track location, and pig-butchering scams are told by their victims.
Mar 31, 2025
ReadFebruary 2025 is dominated by LLM agents: encrypted backdoors that evade audits, a defence against indirect prompt injection, AI search engines citing malicious sites and an agent that compromises an Active Directory network on its own. Beyond AI, the global seizure of DDoS-for-hire services has short-lived effects and the post-quantum Dilithium signature falls to a side channel.
Feb 28, 2025
ReadJanuary 2025 brings the NDSS proceedings. Open-model adapters can hide trojans, and the shared cache of LLM servers leaks other users' prompts. An autonomous car's LiDAR is spoofed at 60 km/h from 110 metres, attackers use Tor to hit cloudless IoT devices, and CSS alone is enough to fingerprint browsers and email clients.
Jan 31, 2025
ReadDecember 2024 is the month of the ACM CCS proceedings. Jailbreaks collected from the web bypass the safeguards of major LLMs. Fuzzing LTE and 5G cores finds 119 vulnerabilities and satellite modems show 18 new attacks. Even FIDO2 keys can be deceived, while address poisoning on Ethereum costs victims millions of dollars.
Dec 31, 2024
ReadNovember 2024 shows LLM agents able to automate a penetration test and backdoors that leak documents from RAG systems. On the infrastructure side, a critical flaw in an RPKI validator may be an intentional backdoor. Nearly half the apps updating IoT devices have flaws, and an e-scooter becomes the target of battery ransomware.
Nov 30, 2024
ReadOctober 2024 brings the first broad benchmarks of LLM agent security: attacks often succeed and defenses hold up poorly. In applied cryptography, four out of five encrypted cloud storage services show serious flaws and compilers undo constant-time protections. A study compares industry and academic DDoS data and finds diverging views.
Oct 31, 2024
ReadSeptember 2024 marks AI security's shift from models to agents: web pages that steal personal data from agents and a defense based on information flow control. Social engineering gets automated with LLM-driven phone calls, while a field study scales back expectations for phishing training. In post-quantum, fault injection attacks hit ML-KEM and ML-DSA on microcontrollers.
Sep 30, 2024
Read