30
MarkSec: Capability-Aware Evaluation of Adversarial Attacks Against LLM Watermarks
MarkSec unifies evaluation of stealing, scrubbing, and spoofing attacks against LLM watermarks with quality-constrained success metrics under shared reporting protocols.
MarkSec is a framework unifying analysis of stealing, scrubbing, and spoofing attacks against LLM watermarks under shared detector calibration, metric definitions, and reporting protocols. It introduces a quality-constrained attack success metric that jointly assesses attack effectiveness and text quality. Experiments across representative watermark families, attacks, LLMs, and datasets show that attacks strongest by watermark removal alone can fall behind general rewriting when success requires acceptable text quality, and stealing-based scrubbers often underperform the best general-scrubbing baselines.
50
Scalable Composition of Byzantine Agreements under Reorder Attacks
Researchers present the first adversary model combining party corruption with channel reordering attacks, establishing tight security thresholds for composed Byzantine agreement protocols.
The paper presents the first adversary model combining party corruption with adversarial channel attacks that reorder messages across multiple Byzantine agreement executions. It proves impossibility results for authenticated BA under parallel composition when n ≤ 3t or n ≤ 2c + 2t + 1, with matching possibility results when n > max{3t, 2c + 2t + 1}. The authors provide general black-box compilers plus erasure-correcting-code variants that achieve constant multiplicative communication overhead for long messages.
25
42
55
Windows Malware Detector as a Compound AI System: Trade-Offs in Accuracy, Efficiency, and Adversarial Robustness
Researchers model industrial Windows malware detection as a Compound AI System, quantifying trade-offs between detection accuracy, efficiency, and adversarial robustness under tiered attacker knowledge.
Industrial Windows malware detectors combine rule-based mechanisms with ML-based static and dynamic analyses, but their architectures are rarely publicly disclosed. The authors propose a methodology balancing detection performance, computational cost, and robustness, plus system-level threat models capturing whole-pipeline evasion rather than isolated components. Experiments on real-world data show training time reductions with marginal detection loss, while more knowledgeable attackers craft increasingly effective adversarial examples. The paper derives deployment guidelines from the observed efficiency-robustness trade-off.
42
55
42
On Identifying Adversarial Intent Injection in AI-Native 6G Networks
Dual-path CNN and AutoEncoder framework detects adversarial intent injection in AI-native 6G networks, reaching 0.97 accuracy and 0.98 F1.
The paper defines a fine-grained threat model for adversarial intent injection in AI-native 6G intent-based networking, where malicious policies are disguised within benign intent flows. It evaluates four injection strategies: stealth-mode, random distribution, increasing frequency, and decreasing frequency. A dual-path detection framework combines a CNN using TF-IDF features for supervised detection with an AutoEncoder trained only on benign data for one-class detection, reaching 0.97 accuracy and 0.98 F1-score, roughly 9% and 36% gains over the state-of-the-art baseline.
35
55
30
30
30
55
30
Staying Ahead of Adversarial AI Through Agentic Source Code Review
Google Threat Intelligence details an agentic AI pipeline with human expert oversight to review source code and outpace AI-enabled attackers.
Google Threat Intelligence researchers argue that adversaries' misuse of AI raises the risk of data theft and extortion when proprietary source code is exposed. They describe a structured agentic source code review pipeline that combines AI models with skeptical validation steps and injected human domain expertise. The team reports a leap in efficacy in finding vulnerabilities before adversaries can exploit them.
45
55
Hackers Steal Active Directory Password Hashes Without Attacking Domain Controllers Directly
Attackers use the DCSync technique to impersonate domain controllers and harvest AD password hashes and Kerberos keys without directly compromising domain controllers, Trellix warns.
Per Trellix, threat actors increasingly abuse Active Directory replication via DCSync, using privileged credentials to invoke DRSGetNCChanges and retrieve NTLM password hashes and Kerberos key material without running code on domain controllers. Capturing the krbtgt account hash enables forging Golden Tickets for persistent, highly privileged domain access. Because malicious replication traffic mimics legitimate DRS/RPC activity, defenders should monitor Windows Security Event ID 4662, restrict replication permissions, and investigate replication requests from non-domain-controller systems.
35
Enterprise Defenses Recovered at the Edge and Collapsed Inside
Picus Labs' Blue Report 2026 finds perimeter prevention at 69% but post-compromise prevention just 37%, with reconnaissance blocked only 10% of the time.
Picus Labs' Blue Report 2026, based on 434,000+ simulated attacks across client production environments in H1 2026, found perimeter prevention effectiveness rose from 62% to 69% while the Post-Compromise Prevention Rate was only 37%. Quiet techniques fared worst: reconnaissance was blocked 10% of the time, registry-based credential access less than 1%, and the alert score stayed at 14% despite logging at a four-year high of 58%. IOC-based prevention fell to 50% from 71% in 2024, and Mimikatz's LSASS path was blocked about 94% while alternative credential-read paths went nearly undetected.
45
Credential Theft: How Attackers Steal & Use Stolen Credentials
Huntress explains how attackers steal credentials through phishing, AitM, infostealers, and dumping, then use them for lateral movement, BEC, and ransomware.
Huntress published an educational overview of credential theft, citing that roughly 70% of confirmed data breaches begin with stolen credentials. It details acquisition methods including phishing, adversary-in-the-middle attacks that capture MFA session tokens, infostealers (nearly a quarter of threats Huntress observed in 2025), Mimikatz-based credential dumping, credential stuffing, and password spraying. The piece then covers post-theft actions such as lateral movement, privilege escalation, account takeover, business email compromise, and ransomware, and closes with behavioral detection guidance and layered prevention strategies.
15
PDoS: A Profitable Denial-of-Service Attack against Proof-of-Work Blockchain Liveness
PDoS attack disrupts Proof-of-Work blockchain liveness profitably by combining miner deterrence signals with parasitic revenue extraction from victim pools.
PDoS is a hybrid incentive-driven denial-of-service attack that combines block header signal deterrence with parasitic revenue extraction from a victim pool's share-reward mechanism. By subsidizing attack costs through the victim pool, it lowers the hash-power threshold required to induce rational miners to shut down, unlike prior attacks such as BDoS that demand sustained attacker losses. The authors show a counterintuitive result: in high-fee or high-MEV environments, higher block value increases the attacker's parasitic revenue and can push the attack past break-even into a self-sustaining or even profitable regime. PDoS is claimed as the first attack demonstrating that disrupting PoW blockchain liveness can be economically self-sustaining.
38
30
InceptionRAG: Stealthy Poisoning Attack Against Retrieval-Augmented Generation
InceptionRAG fragments malicious payloads into dormant passages that trigger LLMs to self-deduce misinformation via multi-hop reasoning, bypassing existing RAG poisoning defenses.
Researchers introduce InceptionRAG, a stealthy corpus poisoning attack against retrieval-augmented generation that splits a malicious payload into a chain of individually harmless dormant passages. When retrieved together, the passages induce LLMs to self-deduce target misinformation through multi-hop reasoning, achieving over 80% attack success rate across three datasets and three LLMs under rigorous adversarial constraints. A zeroth-order suffix optimization (ZOSO) method automates authoritative suffix generation in black-box settings. The authors also propose HODOR, a document isolation defense that decouples adversarial logical dependencies.
54
AI AppSec tools agree on just 5% of security findings
Contrast Security report finds 42 confirmed exploit attempts per application monthly and three AI scanners agreeing on only 5% of findings.
Contrast Security's AppSec Overflow 2026 report, drawing on telemetry from hundreds of thousands of production applications and APIs, found adversaries touch the average application every four minutes with 42 confirmed viable exploit attempts per application monthly, led by untrusted deserialization, path traversal, and method tampering. Legacy flaws Log4Shell and Spring4Shell remain widespread, mean time to exploit fell from over two years in 2018 to under three weeks for most 2025 exploited vulnerabilities, and average critical fix time is 92 days. Three AI scanners set on the same codebase agreed on only 5% of findings, and triaging a 2-million-line codebase scan cost roughly $128,000 versus $315 in API charges. Among exploited CVEs in the dataset, 82% of KEV-listed entries carried EPSS scores of 90% or higher, while CVE-2006-1547 and CVE-2023-38180 were confirmed exploited despite EPSS scores under 25%.
45
30
Certifying Adversarial Robustness of Quantum Classifiers under Known-Readout Query Access
Framework certifies adversarial robustness of quantum classifiers using only measurement statistics and finite-shot outcomes, demonstrated on IBM Quantum hardware.
The paper introduces a measurement-only certification framework for adversarial robustness of quantum classifiers under known-readout query access, requiring no tomography, parameters, or gradients. It returns a lower bound ruling out untargeted errors within a radius and an attack-independent upper bound witnessing an adversarial state, both estimable with finite-sample guarantees. Evaluations show the lower bound tracks exact optima on tractable instances while the upper bound stays informative when standard attacks fail. The method was validated on IBM Quantum hardware using 40 executions of two 8-qubit quantum neural networks.
27
338 Million Attack Simulations Reveal The State Of Enterprise Defense
Picus Labs' Blue Report 2026, from 338 million attack simulations, finds defenses strong at the perimeter but blocking only 37% of post-compromise actions.
Picus Labs' fourth annual Blue Report analyzed over 338 million attack simulations from production environments in H1 2026. Average prevention effectiveness rose from 62% to 69%, but only 37% of attacker actions were blocked after compromise, with reconnaissance and credential theft largely missed. IOC-based malware download prevention fell to 50% from 71% in 2024, and Mimikatz credential dumping from LSASS memory was blocked 94% of the time versus 17% from other memory locations and 3% from registry.
60
30
30
Are Unreachable Nodes Truly Safe? Fully Eclipsing Monero's P2P Network!
Researchers present Nyx and Moros, the first eclipse attacks against Monero nodes behind NATs, requiring no inbound access and demonstrated on mainnet.
The paper presents the first eclipse attacks tailored to unreachable Monero nodes operating behind NATs, requiring no inbound access to the victim. The attacks poison the peerlists of reachable nodes, which relay contamination to unreachable nodes' whitelists, then exploit Monero's outbound connection refresh logic to evict benign neighbors and monopolize all outbound connections. Nyx achieves a complete, persistent eclipse of long-running unreachable nodes in large-scale SEED Emulator simulations, while Moros stealthily eclipses newly joined nodes during bootstrapping and was demonstrated on the Monero mainnet. Countermeasures are proposed.
45
30
30
30
30
30
Why The Vulnerability Backlog Is About To Get Worse
Recorded Future analysis says AI-driven vulnerability discovery and faster weaponization will grow the triage backlog while shrinking defenders' response windows.
Disclosed vulnerabilities rose from roughly 21,000 in 2021 to nearly 50,000 in 2025, while Recorded Future assessed only 446 as actively exploited in 2025. VulnCheck found nearly 29% of 2025 KEV entries were exploited on or before CVE publication. The authors argue AI-assisted discovery and automated exploit development will multiply credible reports, cut disclosure-to-exploit time toward minutes, and force re-evaluation of medium-severity flaws as exploit-chain components.
45
30
A Graph-Based Approach for Mapping Kernel-Level Telemetry to MITRE ATT&CK
Trace2ATT&CK maps eBPF kernel telemetry to MITRE ATT&CK via provenance graphs and RAG with local open-weights LLMs, validated on 347 Atomic Red Team tests.
Trace2ATT&CK collects kernel-level events via eBPF, correlates attacker commands into a provenance graph, and derives compact graph representations suitable for LLM-based reasoning, mapping behavior to MITRE ATT&CK techniques with ranked candidates and rationales. Mapping uses both pure LLM prompting and retrieval-augmented generation grounded in the ATT&CK knowledge base. It was evaluated on 347 Linux Atomic Red Team tests using locally deployed open-weights LLMs. RAG consistently improved ATT&CK mapping over pure prompting, and provenance graphs substantially outperformed raw telemetry, without compromising data confidentiality.
38
Trust-Aware Adaptive Disclosure for Inference Privacy Preservation in Multi-Agent Networks
Researchers propose a trust-aware privacy framework for multi-agent systems that adapts message disclosure to reduce goal inference attacks.
The cs.CR paper addresses privacy-preserving consensus in networked multi-agent systems where observing adversaries attempt to infer each agent's hidden goal from its messages. A Trust-Aware Privacy Control framework uses a trust-dependent stochastic policy to adapt information release, trading off consensus performance and privacy. Experiments show reduced adversarial goal inference accuracy versus representative baselines while maintaining competitive consensus utility, with relevance to deployments such as healthcare management and smart grids.
28
42