REPORTS
Fresh threat intelligence we ingest from public vendor and research feeds — each report linked to its original source. Search, filter by source, and open the reference.
Reports
Newest first. Search, filter by source, open the original.
850 reports · page 14 of 22
arxiv_cs_cr · tlp:amber · 6/15/2026, 4:00:00 AM
Breaking TinyML: Why Quantized Neural Networks Need Domain-Specific Security Analysis arXiv:2606.14427v1 Announce Type: new Abstract: Most TinyML hardware accelerators focus on supporting Quantized Neural Networks (QNNs) to meet stringent constraints on power consumption and size. Despite this, the security aspects of quantization within TinyML hardware remain largely unexplored. Although previous studies indicate that QNNs demonstrate similar or enhanced robustness when com…
Read original ↗https://arxiv.org/abs/2606.14427arxiv_cs_cr · tlp:amber · 6/15/2026, 4:00:00 AM
Securing the Future of IoMT in the Post-Quantum Era: An Edge-Native Federated Learning Approach arXiv:2606.14515v1 Announce Type: new Abstract: Internet of Medical Things (IoMT) devices operate under strict resource constraints while handling highly sensitive health data, making security and privacy critical concerns. Federated learning (FL) further complicates this landscape, as model updates exchanged during training may unintentionally expose private medical information. …
arxiv_cs_cr · tlp:amber · 6/15/2026, 4:00:00 AM
From Shield to Target: Denial-of-Service Attacks on LLM-Based Agent Guardrails arXiv:2606.14517v1 Announce Type: new Abstract: LLM-based guardrails have emerged as a highly effective defense against prompt injection and jailbreak attacks in autonomous agents. However, we reveal that the very reasoning and task-following capabilities enabling this protection introduce a novel vulnerability: attackers can inject crafted data to trap the guardrail in extended reasoning loops, e…
Read original ↗https://arxiv.org/abs/2606.14517arxiv_cs_cr · tlp:amber · 6/15/2026, 4:00:00 AM
Detecting Bot Detection: Prevalence, Techniques, and Implications for Web Measurement Research arXiv:2606.14525v1 Announce Type: new Abstract: Browser automation frameworks are essential tools for security and privacy research on the web, yet bot detection scripts increasingly probe their artifacts, threatening measurement validity as automated browsers may be blocked or served different content. Prior work measures detection deployment, while we measure blocking-induced sam…
Read original ↗https://arxiv.org/abs/2606.14525arxiv_cs_cr · tlp:amber · 6/15/2026, 4:00:00 AM
When Good Verifiers Go Bad: Self-Improving VLMs Can Regress on New Tasks arXiv:2606.14629v1 Announce Type: new Abstract: Verifier-driven self-DPO is a common recipe for self-improving production visual-language models. In this setup, a frozen verifier scores candidate generations, the top- and bottom-scoring candidates form a preference example, and DPO updates the learner. The deployment-time assumption is monotone: a stronger verifier should yield a stronger student. We sh…
Read original ↗https://arxiv.org/abs/2606.14629arxiv_cs_cr · tlp:amber · 6/11/2026, 4:00:00 AM
JailbreakOPT: Tool-Assisted Iterative Jailbreak Prompt Optimization arXiv:2606.11425v1 Announce Type: new Abstract: Jailbreak attacks expose persistent safety weaknesses in large language models (LLMs), but existing stateless single-turn methods face a trade-off: hand-crafted prompts are expressive but static, while iterative prompt optimization can adapt but often relies on low-level mutations that require many target queries. We propose JailbreakOPT, a tool-assisted framew…
Read original ↗https://arxiv.org/abs/2606.11425arxiv_cs_cr · tlp:amber · 6/11/2026, 4:00:00 AM
Systematic Cybersecurity Risk Analysis of European Rail Traffic Management System arXiv:2606.11839v1 Announce Type: new Abstract: European Rail Traffic Management System (ERTMS) is a widely adopted standard unifying train management in the EU. While the standard allows for use cases like fully autonomous driving, cybersecurity has been an afterthought. Risk analysis enables the systematic assessment and prioritization of threats and mitigations. To date, it remains unclear w…
Read original ↗https://arxiv.org/abs/2606.11839arxiv_cs_cr · tlp:amber · 6/11/2026, 4:00:00 AM
Gerrymandering the Warp: Non-Control-Data Attacks on CUDA Collective Decision arXiv:2606.11878v1 Announce Type: new Abstract: CUDA collective operations often sit on security decision paths: votes accept batches, reductions aggregate evidence, shuffles select representatives, and barriers order checked state before use. Such decisions depend not only on computed values, but also on which lanes are represented, what evidence they contribute, which lane speaks for the group, a…
Read original ↗https://arxiv.org/abs/2606.11878arxiv_cs_cr · tlp:amber · 6/11/2026, 4:00:00 AM
Evaluating and Combating the Impact of Concept Drift on the Performance of Machine Learning-Based Phishing Detection Systems arXiv:2606.11471v1 Announce Type: new Abstract: The expansion of the digital domain has resulted in a substantial increase in digital communication, with email emerging as one of the most prominent channels. The proliferation of email communication is apparent in both professional and personal contexts, thereby creating numerous vulnerabilities for mal…
Read original ↗https://arxiv.org/abs/2606.11471arxiv_cs_cr · tlp:amber · 6/11/2026, 4:00:00 AM
Jaguar: Fast Private CNN Inference with Power-of-Two Homomorphic Arithmetic arXiv:2606.11827v1 Announce Type: new Abstract: Hybrid HE/2PC private CNN inference remains bottlenecked by prime-modulus homomorphic arithmetic in convolution and by a precision flow that runs ReLU at doubled bitwidth before invoking a separate truncation protocol. We present Jaguar, a system built on a single design choice--a power-of-two ciphertext ring--that addresses both. The choice enables SPA…
Read original ↗https://arxiv.org/abs/2606.11827arxiv_cs_cr · tlp:amber · 6/11/2026, 4:00:00 AM
Hiding the Trees in the Forest: Building Network Covert Channels with Hash-Based Covert Carrier Filtering arXiv:2606.11532v1 Announce Type: new Abstract: As an effective anti-censorship mechanism, network covert channels can provide data privacy protection and ensure communication security. However, the covertness of existing network covert channels primarily depends on the secrecy of their covert algorithms. With the increasing depth of research in this field, the difficult…
Read original ↗https://arxiv.org/abs/2606.11532arxiv_cs_cr · tlp:amber · 6/11/2026, 4:00:00 AM
When Poison Fails After Retrieval: Revisiting Corpus Poisoning under Chunking and Reranking Pipelines arXiv:2606.11265v1 Announce Type: new Abstract: Retrieval-Augmented Generation (RAG) systems are vulnerable to corpus poisoning attacks that manipulate downstream model outputs through malicious knowledge injection. Existing studies mainly evaluate poisoning under simplified retrieval settings, overlooking practical RAG pipelines involving document chunking, dense retrieval,…
Read original ↗https://arxiv.org/abs/2606.11265arxiv_cs_cr · tlp:amber · 6/11/2026, 4:00:00 AM
VIPIR: A Versatile GPU Framework for Integrating Private Information Retrieval Protocols arXiv:2606.11536v1 Announce Type: new Abstract: While private information retrieval (PIR) enables private database services by fully concealing access patterns, it simultaneously requires high computational throughput, large memory capacity, and substantial memory bandwidth. We introduce VIPIR, a versatile GPU framework that co-designs PIR protocols with GPU acceleration. We develop a un…
Read original ↗https://arxiv.org/abs/2606.11536arxiv_cs_cr · tlp:amber · 6/11/2026, 4:00:00 AM
PriME-Deal: Privacy-Preserving Bilateral Data Trading with Efficient Matchmaking and Auditable Fair Exchange on Blockchain arXiv:2606.11539v1 Announce Type: new Abstract: Bilateral attribute-based access control for data trading must hide policies, provide cryptographic fairness, and avoid trusted third parties. Existing solutions either leak policy information, incur super-linear costs, or rely on trusted dispute resolution. We present PriME-Deal, a non-interactive protocol…
Read original ↗https://arxiv.org/abs/2606.11539arxiv_cs_cr · tlp:amber · 6/11/2026, 4:00:00 AM
WHET: Welding Homomorphic Encryption to Accelerator Architectures arXiv:2606.11541v1 Announce Type: new Abstract: Fully homomorphic encryption (FHE) enables computations on encrypted data without decryption, offering strong data privacy at the expense of substantial computational and memory overheads. Prior efforts have steadily improved FHE performance through cryptographic and algorithmic enhancements or hardware acceleration, yet these two directions have progressed large…
Read original ↗https://arxiv.org/abs/2606.11541arxiv_cs_cr · tlp:amber · 6/11/2026, 4:00:00 AM
Grammar-Constrained Decoding Can Jailbreak LLMs into Generating Malicious Code arXiv:2606.11817v1 Announce Type: new Abstract: Large Language Models (LLMs) are increasingly used for code generation, raising concerns that they may be misused to produce malicious code. Meanwhile, Grammar-Constrained Decoding (GCD) has been widely adopted to improve the reliability of LLM-generated code by enforcing syntactic validity. In this paper, we reveal a counterintuitive risk: this reli…
Read original ↗https://arxiv.org/abs/2606.11817arxiv_cs_cr · tlp:amber · 6/11/2026, 4:00:00 AM
Privacy-Preserving Federated Autoencoder for ECG Anomaly Detection on Edge Devices arXiv:2606.11556v1 Announce Type: new Abstract: Continuous electrocardiography (ECG) monitoring could surface rhythm abnormalities before they escalate into cardiovascular events. However, a deployable system must satisfy three requirements simultaneously: legal-grade privacy (GDPR, HIPAA), real-time inference on constrained edge hardware, and detection quality under non-IID cross-hospital dat…
Read original ↗https://arxiv.org/abs/2606.11556arxiv_cs_cr · tlp:amber · 6/11/2026, 4:00:00 AM
WarpGuard: Protected-Site Control-Flow Integrity for CUDA SASS Binaries arXiv:2606.11871v1 Announce Type: new Abstract: Recent CUDA exploitation work shows that GPU memory bugs can escalate into device-side control-flow corruption, as kernels later consume corrupted return continuations, function pointers, dispatch-table entries, or branch targets. For deployed CUDA binaries, the relevant security boundary is executed NVIDIA SASS, after PTX lowering, inlining, ABI decisions,…
Read original ↗https://arxiv.org/abs/2606.11871arxiv_cs_cr · tlp:amber · 6/11/2026, 4:00:00 AM
A Deterministic Forensic Preprocessing Framework for Heterogeneous Network Datasets: Formal Foundations, Implementation, and Empirical Validation arXiv:2606.11565v1 Announce Type: new Abstract: Digital forensic investigations increasingly depend on preprocessing heterogeneous network evidence from intrusion detection systems, IoT devices, and enterprise traffic logs. Incompatible schemas and timestamp formats hinder evidence correlation and timeline reconstruction, while cur…
Read original ↗https://arxiv.org/abs/2606.11565arxiv_cs_cr · tlp:amber · 6/11/2026, 4:00:00 AM
Defense Against Prompt Inversion Attacks: An Information-Theoretic Approach for LLM Collaborative Inference arXiv:2606.11592v1 Announce Type: new Abstract: Collaborative edge-cloud inference enables resource-constrained devices to leverage large language models (LLMs) by offloading partial computation to cloud servers. However, transmitting intermediate activations exposes sensitive user prompts to prompt inversion attacks, where an adversary reconstructs the original input …
Read original ↗https://arxiv.org/abs/2606.11592arxiv_cs_cr · tlp:amber · 6/11/2026, 4:00:00 AM
SwarmSense-DNN: A Trustworthy and Decentralized Neural Framework for Proactive Anomaly Defense in Consumer IoT arXiv:2606.11803v1 Announce Type: new Abstract: The rapid growth of consumer IoT devices has introduced unprecedented challenges in trustworthy anomaly detection against AI-enabled cyber threats, requiring real-time, privacy-preserving, and scalable defense mechanisms. Traditional centralized strategies face critical limitations, including communication bottlenecks,…
Read original ↗https://arxiv.org/abs/2606.11803arxiv_cs_cr · tlp:amber · 6/11/2026, 4:00:00 AM
Sovereign Assurance Boundary: Certificate-Bound Admission for Agentic Infrastructure arXiv:2606.11632v1 Announce Type: new Abstract: Agentic infrastructure introduces a critical control-plane authorization problem: non-deterministic reasoning systems can propose high-stakes mutations to production resources, yet existing security mechanisms -- such as identity and access management (IAM), policy engines, consensus protocols, and audit logs -- either enforce static, context-u…
Read original ↗https://arxiv.org/abs/2606.11632arxiv_cs_cr · tlp:amber · 6/11/2026, 4:00:00 AM
Dummy Backdoor as a Defense: Removing Unknown Backdoors via Shared Internal Mechanisms for Generative LLMs arXiv:2606.11648v1 Announce Type: new Abstract: Backdoor attacks pose a serious threat to the safety and reliability of Large Language Models (LLMs), as they cause models to behave normally on clean inputs while producing attacker-specified responses when hidden triggers are present. Removing such unknown backdoors is particularly challenging when the defender does not …
Read original ↗https://arxiv.org/abs/2606.11648arxiv_cs_cr · tlp:amber · 6/11/2026, 4:00:00 AM
A Robust Framework for Sybil Attack Detection in Vehicular Ad Hoc Networks arXiv:2606.11667v1 Announce Type: new Abstract: Sybil attacks create an illusion of traffic congestion by utilizing fake identities, which undermines the reliable and safe operation of vehicular ad hoc networks (VANETs). Existing detection mechanisms struggle to effectively handle Sybil attacks as they are (i) susceptible to high false positive rates (FPR) due to the overlapping trajectories of both S…
Read original ↗https://arxiv.org/abs/2606.11667arxiv_cs_cr · tlp:amber · 6/11/2026, 4:00:00 AM
MHOT: Height-Optimized Authenticated Data Structure for Blockchain State Commitment arXiv:2606.11736v1 Announce Type: new Abstract: State root computation dominates (78%) blockchain block processing time. Ethereum's canonical authenticated data structure, i.e., Merkle Patricia Trie (MPT), suffers from severe tree-height growth and is vulnerable to \textit{Nurgle attacks} (SP'24), where adversaries inflate path depth via hash collisions and degrade system performance at negli…
Read original ↗https://arxiv.org/abs/2606.11736arxiv_cs_cr · tlp:amber · 6/11/2026, 4:00:00 AM
Runtime Skill Audit: Targeted Runtime Probing for Agent Skill Security arXiv:2606.11671v1 Announce Type: new Abstract: Agent skills let LLM agents reuse instructions, resources, tools, and workflows, but they also create a new place for malicious behavior to hide. A skill may look benign in its documentation or code while becoming harmful only when it is invoked with particular user requests, local assets, persistent state, or multi-step tool interactions. This makes purely …
Read original ↗https://arxiv.org/abs/2606.11671arxiv_cs_cr · tlp:amber · 6/11/2026, 4:00:00 AM
MPC-Patch-Bench: Security-Aware LLM Code Patch for Multi-Party Computation arXiv:2606.11416v1 Announce Type: new Abstract: Repository-level benchmarks for evaluating Large Language Model (LLM) code repair on Secure Multi-Party Computation (MPC) software do not yet exist, and directly transplanting general-purpose benchmarks such as SWE-bench fails on three structural fronts: (i) MPC repositories are dominated by generic Python infrastructure rather than cryptographic logic; …
Read original ↗https://arxiv.org/abs/2606.11416arxiv_cs_cr · tlp:amber · 6/11/2026, 4:00:00 AM
A VPN-as-a-Service Tailored Enabler for Computing-constrained Environments arXiv:2606.11729v1 Announce Type: new Abstract: Industry has embraced Zero Trust (ZT) architectural tenets and implementations for cloud-native environments, following stricter security requirements to both internal and external tenants. Among others, these approaches combine fine-grained identity management and monitoring for both inventorying and better analysing the devices' security posture for ov…
Read original ↗https://arxiv.org/abs/2606.11729arxiv_cs_cr · tlp:amber · 6/11/2026, 4:00:00 AM
Can Open-Source LLM Agents Replace Static Application Security Testing Tools? An Empirical Assessment arXiv:2606.11672v1 Announce Type: new Abstract: This paper explores the value of agentic AI tools for cybersecurity purposes. We evaluate the efficacy of a general-purpose GenAI Large Language Model- (GenAI-) based agent when powered by three different Ollama-hosted general-purpose open source models. We assess each agent's performance using precision, recall, false positive…
Read original ↗https://arxiv.org/abs/2606.11672arxiv_cs_cr · tlp:amber · 6/11/2026, 4:00:00 AM
T2S: A Rehearsal-Based Approach for Extraction-Resistant Model Watermarking arXiv:2606.11698v1 Announce Type: new Abstract: Model watermarking safeguards AI model intellectual property by embedding distinctive knowledge that induces unique behavioral signatures. The primary technical challenge lies in ensuring watermark robustness against various post-processing attacks on the watermarked model. Model extraction attacks emerge as the most severe threat, where adversaries exp…
Read original ↗https://arxiv.org/abs/2606.11698arxiv_cs_cr · tlp:amber · 6/10/2026, 4:00:00 AM
The Linux IOCTL Census: A Source-Derived Database of the Linux Kernel Control-Code Surface arXiv:2606.10290v1 Announce Type: new Abstract: The ioctl system call is Linux's catch-all device-control interface. A userspace program opens a device node and hands the driver a numeric command code and an argument buffer, and the driver does whatever that code means, whether configuring hardware, reading back state, or moving data into and out of the kernel. Drivers define these com…
Read original ↗https://arxiv.org/abs/2606.10290arxiv_cs_cr · tlp:amber · 6/10/2026, 4:00:00 AM
RECON: An LLM-Enhanced Backward Constraint Analysis Framework arXiv:2606.10264v1 Announce Type: new Abstract: While traditional techniques, such as symbolic execution, provide a principled foundation for precise constraint reasoning in program analysis, they struggle to scale to modern software systems mainly due to path explosion, the need for function modeling, and the loss of semantic intent at low-level program representations. In complex execution environments such as A…
Read original ↗https://arxiv.org/abs/2606.10264arxiv_cs_cr · tlp:amber · 6/10/2026, 4:00:00 AM
Local Is Not a Sufficient Privacy Boundary: Governing OS-Integrated On-Device AI arXiv:2606.10173v1 Announce Type: new Abstract: As AI systems move into operating systems, privacy no longer turns only on whether a model runs locally. A local assistant may assemble email, calendar entries, files, screenshots, notifications, and app intents; retain embeddings or summaries; invoke tools; emit telemetry; or route difficult requests to cloud infrastructure. Local inference reduce…
Read original ↗https://arxiv.org/abs/2606.10173arxiv_cs_cr · tlp:amber · 6/10/2026, 4:00:00 AM
From Data Heterogeneity to Convergence: A Data-Centric Review of Federated Learning arXiv:2606.10595v1 Announce Type: new Abstract: Federated Learning (FL) has emerged as a promising solution for data hunger in centralized learning. This paradigm enables privacy with multiple clients to train a shared-task model collaboratively without exposing their local data. While being a key component in any learning system, data is also a primary source of vulnerabilities and challenge…
Read original ↗https://arxiv.org/abs/2606.10595arxiv_cs_cr · tlp:amber · 6/10/2026, 4:00:00 AM
A Hybrid Edge-Cloud Architecture for Low-Latency Entitlement Verification in Resource-Constrained Devices arXiv:2606.10536v1 Announce Type: new Abstract: As digital media consumption shifts toward large-scale Over-the-Top (OTT) platforms, the efficiency of the control plane, specifically entitlement and identity verification, has become a critical factor in user experience. Current architectures often rely on synchronous cloud-tethered validation flows that introduce signifi…
Read original ↗https://arxiv.org/abs/2606.10536arxiv_cs_cr · tlp:amber · 6/10/2026, 4:00:00 AM
Assessing Automated Prompt Injection Attacks in Agentic Environments arXiv:2606.10525v1 Announce Type: new Abstract: Indirect prompt injection poses a critical threat to LLM agents that interact with untrusted external data, yet automated attack methods--proven effective for jailbreaking--remain underexplored in realistic agentic settings. We present a comprehensive empirical evaluation of automated prompt injection attacks against LLM agents, adapting both white-box (GCG) a…
Read original ↗https://arxiv.org/abs/2606.10525arxiv_cs_cr · tlp:amber · 6/10/2026, 4:00:00 AM
A Deployment-Oriented Framework for Explainable AI-Assisted eBPF/XDP Mitigation at the IoT Edge arXiv:2606.10508v1 Announce Type: new Abstract: Internet of Things (IoT) deployments combine heterogeneous, resource-constrained devices with weak security configurations, exposed services, limited logging, patching constraints, and long lifecycles. Signature- and threshold-based controls remain useful baselines, but they are insufficient as standalone mechanisms in dynamic IoT ne…
Read original ↗https://arxiv.org/abs/2606.10508arxiv_cs_cr · tlp:amber · 6/10/2026, 4:00:00 AM
When VR Meets BCI: (Un)Observable Brainwave-aware Privacy Reconstruction in the Metaverse via Unrestricted Inbuilt Motion Sensors arXiv:2606.10502v1 Announce Type: new Abstract: Metaverse devices, such as virtual reality (VR), have seen substantial development and widespread applications in numerous areas. Although recent studies have revealed privacy leakages in VR, these vulnerabilities were limited in the scope of observable behaviors in virtual scenes (e.g., what a user …
Read original ↗https://arxiv.org/abs/2606.10502arxiv_cs_cr · tlp:amber · 6/10/2026, 4:00:00 AM
AgentCanary: A Security Evaluation Framework for Autonomous AI Agents in Real Executable Environments arXiv:2606.10484v1 Announce Type: new Abstract: Autonomous AI agents have driven the transition from conversation to task execution, shifting security failures from textual deception to system compromise. Although security evaluation is crucial for proactive risk prevention, prior work is constrained by fundamental bottlenecks, including fragmented risk coverage, static or l…
Read original ↗https://arxiv.org/abs/2606.10484arxiv_cs_cr · tlp:amber · 6/10/2026, 4:00:00 AM
HE-DAP: Homomorphic Encryption-based Dynamic Adaptive Parameter Optimization for Statistical Computation arXiv:2606.10477v1 Announce Type: new Abstract: Homomorphic encryption (HE) enables privacy-preserving analytics but remains hindered by high computational overhead. We find that the inverse square root-a key primitive in many statistical and machine learning workloads-exhibits inconsistent and often suboptimal performance across HE libraries and hardware. This stems from…
Read original ↗https://arxiv.org/abs/2606.10477