Today's cyber intelligence queue

Are AI tutors safe for your kids?

An evidence-built Forensia brief is ready now; publisher prose remains at the original source.

Corporate Data Stolen in Levi Strauss Cyberattack

An evidence-built Forensia brief is ready now; publisher prose remains at the original source.

Solidity Pro VS Code Extensions Steal Crypto Wallets, API Keys, and Credentials

An evidence-built Forensia brief is ready now; publisher prose remains at the original source.

OpenAI's Next AI Model Astra Shows Cyber Performance Strong Enough to Trigger Pause

An evidence-built Forensia brief is ready now; publisher prose remains at the original source.

Critical Flaws Discovered in Belgian eID Software Used by 2 Million People

An evidence-built Forensia brief is ready now; publisher prose remains at the original source.

SoK: Cryptographic Key Recovery for Cryptoasset Custody and Financial Technologies

SoK: Cryptographic Key Recovery for Cryptoasset Custody and Financial Technologies arXiv:2608.07104v1 Announce Type: new Abstract: Cryptoasset systems often bind cryptographic key control to financial control: losing a wallet seed, custody share, hardware device, or smart-account credential can remove spend authority, while compromised recovery can enable theft. Existing work treats recovery through separate vocabularies--key backup, secret sharing, account recovery, credent…

Soft Redaction of Image Provenance via Zero-Knowledge Proofs

Soft Redaction of Image Provenance via Zero-Knowledge Proofs arXiv:2608.07063v1 Announce Type: new Abstract: Content provenance standards, such as C2PA, are increasingly used to attach signed records of origin, editing history, and rights to digital images. However, provenance transparency can conflict with privacy -- assertions that strengthen trust in an image may also reveal sensitive information about the creator or capture context. We propose soft redaction for image pr…

Effects of parental controls in the context of Digital Forensics

Effects of parental controls in the context of Digital Forensics arXiv:2608.07016v1 Announce Type: new Abstract: Parental control systems are designed to protect minors online, but can inadvertently obstruct digital forensic investigations. When enabled, these systems restrict administrative privileges, disable debugging options, and alter data accessibility, complicating evidence acquisition and analysis. This study empirically examines the impact of Microsoft, Google, and …

HarnessSafe: Evaluating Safety Across Persistent Carriers in Agent Harnesses

HarnessSafe: Evaluating Safety Across Persistent Carriers in Agent Harnesses arXiv:2608.06984v1 Announce Type: new Abstract: Modern agent harnesses persist state across tasks and sessions through persistent carriers like memory, skills, tools, and shared artifacts. However, this capability creates delayed safety risks: attacker-influenced content can cross system boundaries and later affect the execution of a benign request. Existing benchmarks typically focus on a few carri…

Casting the Net! Revisiting MasterFace Impersonation Attacks

Casting the Net! Revisiting MasterFace Impersonation Attacks arXiv:2608.06952v1 Announce Type: new Abstract: Impersonation is a fundamental security threat in face recognition systems (FRSs). While the security of FRSs has been challenged by various attack vectors, under realistic adversarial capabilities, e.g., a limited number of decision-only authentication trials and no internal system knowledge, most attack techniques become infeasible. As a result, impersonation by zer…

When Context Bites: Detecting RAG Poisoning via Document-Level Attention Collapse

When Context Bites: Detecting RAG Poisoning via Document-Level Attention Collapse arXiv:2608.06947v1 Announce Type: new Abstract: Retrieval-augmented generation (RAG) is indispensable for enhancing large language models. However, RAGs are increasingly susceptible to poisoning attacks, in which adversarial documents are injected to manipulate generator outputs. Previous methods rely on output-side signals such as perplexity and consistency checks to detect such attacks. Never…

Rigid-Covert GNSS Spoofing of UAV Swarms: A Structural Blind Spot, Its Detection Limit, and Absolute-Anchor Defenses

Rigid-Covert GNSS Spoofing of UAV Swarms: A Structural Blind Spot, Its Detection Limit, and Absolute-Anchor Defenses arXiv:2608.06885v1 Announce Type: new Abstract: Cooperative UAV-swarm defenses commonly cross-check GNSS positions against measured inter-drone geometry. We show that this relative-geometry channel has a structural blind spot: a common, slowly varying translation (a rigid-covert shift, RigidShift) preserves all pairwise distances and is therefore unobservable …

SynChain: Inducing Computer-Use Agent Systems to Construct Their Own Attack Chains

SynChain: Inducing Computer-Use Agent Systems to Construct Their Own Attack Chains arXiv:2608.06862v1 Announce Type: new Abstract: Computer-use agents~(CUAs) have transformed large language models into persistent execution systems capable of generating, storing, and reusing artifacts like skills and memory entries. However, existing security defenses largely treat attacks as externally triggered or temporally bounded, leaving a critical gap in addressing how compromise can p…

Understanding and Improving Model Editing for Secure Code Generation

Understanding and Improving Model Editing for Secure Code Generation arXiv:2608.06848v1 Announce Type: new Abstract: Large language models (LLMs) are widely used for code generation, yet they can reproduce vulnerable implementations learned from insecure training patterns. Prior work has mainly explored inference-time hardening, which reduces insecure generations without modifying the target model but relies on auxiliary components and adds runtime overhead. We conduct the f…

MIFA: An MILP-based Framework for Improving Differential Fault Attacks

MIFA: An MILP-based Framework for Improving Differential Fault Attacks arXiv:2608.06837v1 Announce Type: new Abstract: At ASIACRYPT 2021, Baksi et al. introduced DEFAULT, a block cipher designed to algorithmically resist Differential Fault Attack (DFA), claiming 64-bit DFA security regardless of the number of injected faults. At EUROCRYPT 2022, Nageler et al. demonstrated that DEFAULT's claimed DFA resistance can be broken by applying an information-combining technique. More…

POKEx: Performance analysis of POKE-key exchange and SIDH-variants

POKEx: Performance analysis of POKE-key exchange and SIDH-variants arXiv:2608.06826v1 Announce Type: new Abstract: In this paper, we present a comparative performance analysis of the POKE-based key exchange and SIDH variants. SIDH gained attention for its small key size and efficient performance, and has been selected as an alternate candidate in NIST PQC Round 4. However, following the key recovery attack by Castryck and Decru in 2022, SIDH was shown to be vulnerable to pol…

On a General Theoretical Framework for Radio Frequency Fingerprint-Based Authentication

On a General Theoretical Framework for Radio Frequency Fingerprint-Based Authentication arXiv:2608.06805v1 Announce Type: new Abstract: While radio frequency fingerprint (RFF)-based wireless device authentication has been widely studied across different datasets and scenarios, there still lacks a fundamental theory to explain why and how RFF can serve as a reliable device identity, significantly hindering the practical application of such an authentication technology. In thi…

LoRAScan: Detecting Backdoor Prompts in Low-Rank Adapters for Large Language Models via Down-Projection Activation Spikes

LoRAScan: Detecting Backdoor Prompts in Low-Rank Adapters for Large Language Models via Down-Projection Activation Spikes arXiv:2608.06795v1 Announce Type: new Abstract: Low-rank adaptation (LoRA) enables efficient specialization and distribution of large language models through compact adapters. However, untrusted adapters introduce a supply-chain threat: a backdoored adapter can cause a model to generate harmful content, malicious code, political propaganda, or covert adve…

Retrieval-Constrained Policy Optimization for Attack Technique Extraction from Cyber Threat Intelligence

Retrieval-Constrained Policy Optimization for Attack Technique Extraction from Cyber Threat Intelligence arXiv:2608.06778v1 Announce Type: new Abstract: Mapping cyber threat intelligence (CTI) text to MITRE ATT&CK techniques is essential for structured threat analysis, yet manual annotation is costly and does not scale. The ATT&CK taxonomy comprises several hundred attack techniques, and a single CTI passage may describe multiple techniques, making accurate and complete extr…

Tight Security for BBS Signatures

Tight Security for BBS Signatures arXiv:2608.06724v1 Announce Type: new Abstract: This paper studies the concrete security of BBS signatures (Boneh, Boyen, Shacham, CRYPTO '04; Camenisch and Lysyanskaya, CRYPTO '04), a popular algebraic construction of digital signatures which underlies practical privacy-preserving authentication systems and is undergoing standardization by the W3C and IRTF. Sch\"age (Journal of Cryptology '15) gave a tight standard-model security proof unde…

Policy-Masked Private Experts: Auditable and Reversible Capability Access Control in Sparse MoE Models

Policy-Masked Private Experts: Auditable and Reversible Capability Access Control in Sparse MoE Models arXiv:2608.06690v1 Announce Type: new Abstract: Most language-model access controls regulate behavior while leaving the same computation available to every request. We study a different systems question: can trusted authorization determine which newly trained parameters are reachable by the forward pass? Policy-Masked Private Experts freezes a pretrained sparse Mixture-of-E…

CyberLLM: A Multi-Agent LLM Framework for Autonomous Detection and Guarded Response in Automotive Cybersecurity

CyberLLM: A Multi-Agent LLM Framework for Autonomous Detection and Guarded Response in Automotive Cybersecurity arXiv:2608.06651v1 Announce Type: new Abstract: Software-Defined Vehicles (SDVs) expand the automotive attack surface across source code, runtime logs, and deployment topologies, while safety constraints forbid autonomous agents from acting without oversight. This paper presents CyberLLM, a multi-agent, LLM-orchestrated framework that autonomously detects vulnerabi…

From Documentation to Zero-day Vulnerabilities: LLM-Driven Fuzzing of JavaScript Engines in PDF Readers

From Documentation to Zero-day Vulnerabilities: LLM-Driven Fuzzing of JavaScript Engines in PDF Readers arXiv:2608.06641v1 Announce Type: new Abstract: Existing fuzzers for PDF readers rely on simple test cases that involve only individual API calls, leading to limited coverage and potentially missing vulnerabilities that require sequences of API calls. To address these limitations, we propose PDFuzzer, a novel PDF engine fuzzer that automatically generates complex and meani…

WhiteNet: Robust Identification of Overlapping IEEE 802.11 Signals Across Unseen Channels

WhiteNet: Robust Identification of Overlapping IEEE 802.11 Signals Across Unseen Channels arXiv:2608.06581v1 Announce Type: new Abstract: Deep learning (DL) classifiers trained on I/Q samples achieve high accuracy for IEEE 802.11 protocol identification of overlapping signals, but their performance degrades sharply when channel conditions at deployment differ from those encountered during training. We present WhiteNet, a framework that addresses the problem of channel variab…

Model Confidence Under Answer-Preserving Attacks: An Informativeness-Manipulability Frontier

Model Confidence Under Answer-Preserving Attacks: An Informativeness-Manipulability Frontier arXiv:2608.06571v1 Announce Type: new Abstract: Deployed vision-language systems often gate their answers on confidence, making confidence robustness relevant to oversight. We study confidence readouts under white-box, image-only attacks constrained to preserve the generated answer byte-identically. Under a reachability assumption, an unmovable readout cannot outperform the answer-st…

Canonicalization Failures as a Recurring Vulnerability Class: Representation Divergence in Cryptographic Systems and Its Avoidance

Canonicalization Failures as a Recurring Vulnerability Class: Representation Divergence in Cryptographic Systems and Its Avoidance arXiv:2608.06508v1 Announce Type: new Abstract: Cryptographic systems operate on bytes but mean semantic objects. The translation between the two is rarely unique. Where this uniqueness is not enforced, an attack surface opens up as soon as a hash, a signature, replay protection, or consensus identity depends on the representation. The same class…

StepJack: Benchmarking Computer-Use Agent Safety Against Multi-Step Indirect Prompt Injection

StepJack: Benchmarking Computer-Use Agent Safety Against Multi-Step Indirect Prompt Injection arXiv:2608.06477v1 Announce Type: new Abstract: Computer-use agents (CUAs) face a growing threat from indirect prompt injection, where adversarial instructions are planted in the environment such as web pages. In this paper, we introduce multi-step indirect prompt injection, a new attack class against CUAs in which the adversarial goal is decomposed into multiple innocuous-looking s…

CyberForge: Verified Vulnerability Injection at Repository Level for Cybersecurity Agent Training

CyberForge: Verified Vulnerability Injection at Repository Level for Cybersecurity Agent Training arXiv:2608.06471v1 Announce Type: new Abstract: Despite recent advances, frontier large language model (LLM) agents remain limited in discovering and patching complex vulnerabilities in real-world software. Generally available agents can already aid attackers, who only need to find one exploitable weakness, while defenders must continuously identify and patch all vulnerabilities…

Fairis: Fairness-Aware Aggregation with Provable Influence Containment against Fairness Poisoning Attacks in Collaborative Machine Learning

Fairis: Fairness-Aware Aggregation with Provable Influence Containment against Fairness Poisoning Attacks in Collaborative Machine Learning arXiv:2608.06469v1 Announce Type: new Abstract: Collaborative machine learning among financial institutions must be both group-fair and robust against deliberate adversarial manipulation. Existing fairness-aware aggregation methods remain formally vulnerable to fairness poisoning: a malicious client maximizing group disparity while prese…

WorldMark: A Plug-and-Play World Knowledge Interface for Cross-Host Language Model Watermarking

WorldMark: A Plug-and-Play World Knowledge Interface for Cross-Host Language Model Watermarking arXiv:2608.06416v1 Announce Type: new Abstract: Watermarking traces the provenance of text produced by large language models by embedding statistically detectable signals during decoding. Existing schemes fall into logits-based, sampling-based, entropy-aware, and adaptive-strength families, yet all of them place watermark signals according to local token statistics. In the open-en…

Show, Don't Tell: What Evo Continuous Offensive Security Found in a Real Enterprise SaaS

An evidence-built Forensia brief is ready now; publisher prose remains at the original source.

Kernel prepatch 7.2-rc7

An evidence-built Forensia brief is ready now; publisher prose remains at the original source.

Four weekend stable kernel updates

An evidence-built Forensia brief is ready now; publisher prose remains at the original source.

Critical One-Click Vulnerability in Atlassian’s Rovo AI Exposed Enterprise Data

An evidence-built Forensia brief is ready now; publisher prose remains at the original source.

Atlassian Rovo Can Be Tricked Into Sending Jira and Confluence Data to Attackers

An evidence-built Forensia brief is ready now; publisher prose remains at the original source.

New CSS Attacks Can Break Webmail Defenses to Steal Passwords and Tokens

An evidence-built Forensia brief is ready now; publisher prose remains at the original source.

Metabase Zero-Day Exploited in Wild Allows Admin Access Without Authentication

An evidence-built Forensia brief is ready now; publisher prose remains at the original source.

N-able Issues N-central Hotfix 2 as Attackers Reach Managed Systems and Persist

An evidence-built Forensia brief is ready now; publisher prose remains at the original source.

Progress Kemp LoadMaster Flaw Hits CISA KEV After 792 Reported Exploit Attempts

An evidence-built Forensia brief is ready now; publisher prose remains at the original source.