Spiking neural networks (SNNs) are increasingly studied for network intrusion detection, but comparative evidence on how neuron models and spike encodings affect performance remains limited. Evaluation choices can influence results when preprocessing, capture structure, or scenario information crosses the train--test boundary. We evaluate nine snnTorch neuron families with three spike encodings, yielding 27 SNN configurations across four intrusion-detection benchmarks. We screen the design space and then repeat the evaluation using train-only transforms, seed-independent partitions, and capture- or scenario-aware separation. In our study, LeakyParallel/latency ranked first in both 27-configuration evaluations. The leading configurations identified during screening also remained largely consistent under confirmation, indicating that screening preserved the ordering useful for design selection even when the measured performance changed under the stricter protocol. We then examine what latency coding contributes by holding the active spike set fixed and changing only its temporal organization. At the main T=25 operating point, mapping feature magnitude to spike time improved macro-F1 on all five confirmation protocols, while spreading the same spikes through time without that mapping could either improve or reduce performance. This shows that the effect of latency coding comes from both the information carried by spike time and how those spikes interact with the temporal dynamics of the network. Finally, sparse input encoding does not directly translate into sparse internal activity, although latency coding requires fewer fanout-weighted operations than rate coding in the evaluated models. Overall, the results show that SNN design choice, evaluation protocol, spike-timing representation, and computational activity should be examined separately when applying SNNs to static network-flow data.
Raj Patel, Shaswata Mitra, David Amebley et al.· 0 citations
Collaborative perception (CP) enables connected and autonomous vehicles to share sensor data and jointly reason about their environment. To defend against adversaries that fabricate or manipulate shared data, existing systems employ cross-vehicle inconsistency detection and trust estimation, penalizing vehicles whose observations conflict with the majority. In this work, we show that these defenses themselves introduce a new attack surface. We present TrustFlip, a novel attack that weaponizes consistency-based defenses to poison the trust assigned to benign vehicles. Instead of injecting false data into the collaboration pipeline, it deploys physical adversarial objects that are genuine but induce inconsistent observations among benign vehicles. The resulting inconsistencies are misattributed by the defense to the targeted vehicle, causing its trust score to degrade and eventually leading to its downweighting or exclusion from collaboration. Consequently, the system loses reliable sensing contributors, degrading perception capability and potentially inducing safety-critical failures. We evaluate TrustFlip across multiple collaborative perception architectures and defense mechanisms. Our results show that state-of-the-art defenses can be significantly affected: the attack removes the targeted benign vehicle from collaboration in up to 87.7% of scenarios and drops Average Precision (AP) by up to 13%. As an initial mitigation, we introduce TrustReflect, a lightweight self-reflection mechanism that marks disputed regions as uncertain and excludes them from trust evaluation, reducing the attack success rate by 35-100%.
Yutong Liu, Chenyi Wang, Ming F. Li et al.· 0 citations
Large language models (LLMs) are increasingly being used in network operations (NetOps) and artificial intelligence for IT operations (AIOps) for tasks ranging from telemetry retrieval and incident diagnosis to configuration planning and bounded remediation. As these systems acquire greater access to operational tools, the central question is no longer only what an LLM can do, but whether operational assurance increases commensurately with the authority granted to it. This survey examines that question through a structured, evidence-stratified review of agentic NetOps and AIOps. We organise the field around autonomy, tool scope, evidence traces, assurance controls, evaluation, security, and governance, and introduce an operational assurance contract that links each autonomy level to permitted tools, required evidence, independent gates, execution budgets, rollout and rollback duties, and audit requirements. The synthesis reveals a capability--assurance gap: evidence is comparatively strong for read-oriented assistance and tool-grounded diagnosis, but becomes substantially less complete as systems approach configuration change, bounded execution, and closed-loop operation. We therefore argue that evaluation should move beyond static question answering and model accuracy towards workflow-level assessment of evidence quality, tool use, policy and invariant compliance, staged execution, recovery, calibration, cost, and human intervention. We also examine prompt-borne attacks, poisoned or stale operational evidence, excessive agency, privilege boundaries, and weak auditability. Taken together, the survey frames agentic NetOps and AIOps as constrained operational control, in which useful autonomy depends on independently enforced assurance rather than model capability alone.
Muhammad Bilal, Jon Crowcroft, Ruizhi Wang et al.· 0 citations
Local fine-tuning datasets routinely contain sensitive secrets such as API keys, personal identifiers, and financial records. Although "local offline fine-tuning" is often viewed as a privacy boundary, we reveal that compromised model code is sufficient to steal them. Current passive pretrained-weight poisoning attacks, while effective for natural language, fundamentally fail to capture such sparse high-entropy targets due to their reliance on probabilistic semantic prefixes. To bridge this gap, we identify and exploit a practical but overlooked supply-chain vector -- malicious model code camouflaged as standard architectural definitions to realize a paradigm shift from passive weight poisoning to active execution hijacking. We introduce a deterministic full-chain memorization mechanism: it locks onto token-level secrets in dynamic computation flows via online tensor-rule matching, and leverages value-gradient decoupling to stealthily inject attack gradients, overcoming gradient drowning to force model memorization. Furthermore, we achieve, for the first time, attacker-verifiable secret stealing through black-box queries that precisely distinguishes true leakage from hallucination. Our attack achieves over 98% Strict ASR in the default LoRA setting with limited primary-task utility degradation and effectively evades defense measures including semantic safety filtering, code auditing, and perplexity-based detection.
Zi Li, Tian Zhou, Wenze Li et al.· 0 citations
Reach audiences
Advertise in front of researchers, engineers, and readers.
AI agents are autonomous systems that combine LLMs with external tools to solve complex tasks. While such tools extend capability, improper tool permissions introduce security risks such as indirect prompt injection and tool misuse. We characterize these failures as unbalanced tool-driven agency. Agents may retain unnecessary permissions (excessive agency) or fail to invoke required tools (insufficient agency), amplifying the attack surface and reducing performance. We introduce AgenTRIM, a framework for detecting and mitigating tool-driven agency risks without altering an agent's internal reasoning. AgenTRIM addresses these risks through complementary offline and online phases. Offline, AgenTRIM reconstructs and verifies the agent's tool interface from code and execution traces. At runtime, it enforces per-step least-privilege tool access through adaptive filtering and status-aware validation of tool calls. Evaluating on the AgentDojo benchmark, AgenTRIM substantially reduces attack success while maintaining high task performance. Additional experiments show robustness to description-based attacks and effective enforcement of explicit safety policies. Together, these results show that AgenTRIM provides a practical, capability-preserving approach to safer tool use in LLM-based agents.
Roy Betser, Amit Giloni, Shamik Bose et al.· 0 citations
Code-capable large language model (LLM) agents are embedded in software engineering workflows where they can read, write, and execute code, raising "jailbreak" stakes beyond text-only settings. Prior evaluations emphasize refusal or harmful-text detection, leaving open whether agents compile and run malicious programs. We present JAWS-Bench (Jailbreaks Across WorkSpaces), a benchmark spanning three escalating workspace regimes mirroring attacker capability: empty (JAWS-0), single-file (JAWS-1), and multi-file (JAWS-M). We pair it with a hierarchical, executable-aware Judge Framework that tests (i) compliance, (ii) attack success, (iii) syntactic correctness, and (iv) runtime executability to measure deployable harm. Across seven LLM backends from five families, prompt-only attacks in JAWS-0 achieve 61% compliance; 58% are harmful, 52% parse, and 27% run end-to-end. In JAWS-1, compliance reaches ~100% for stronger models with a mean ASR (Attack Success Rate) ~71%; JAWS-M raises mean ASR to ~75%, with 32% runnable attack code. Wrapping an LLM in an agent increases ASR by 1.6$\times$, by overturning initial refusals during planning and tool use. Additional evaluations with SWE-Agent and OpenAI Codex exhibit similar trends, indicating that JAWS-Bench can be reused across multiple agent frameworks. Category analyses identify which attack classes are most vulnerable and deployable, motivating execution-aware defenses and refusal-preserving agent designs.
Shoumik Saha, Jifan Chen, Sam Mayers et al.· 0 citations
Jailbreak attacks bypass the safety alignment of large language models (LLMs) to elicit harmful outputs, yet the vast parameter space makes diagnosing the underlying failure mechanisms extremely challenging. We present NeuroBreak, a visual analytics system that helps experts progressively unpack jailbreak mechanisms from layer-level semantics down to neuron-level behaviors. A layer-wise probing pipeline traces how harmful representations evolve across layers, while a dual-dimensional character--behavior categorization reveals each safety-related neuron's inherent tendency and contextual contribution. These analyses are made interpretable through tailored visualization designs: a task-driven probing projection that reveals safety decision boundaries, a dual-stream semantic evolution flow that traces cross-layer semantic shifts, and a character--behavior chord graph that unifies neuron roles, attribution scores, and collaborative relations in a single view with in-situ causal verification. Quantitative evaluations and case studies show that NeuroBreak uncovers safety failure causes and provides actionable insights for strengthening LLM defenses.
Chuhan Zhang, Ye Zhang, Bowen Shi et al.· 0 citations
Large language models (LLMs) are increasingly used for code generation, making reliable identification of machine-generated code important for attribution, tracking, and misuse detection. Existing code watermarking methods are dominated by N-gram-based schemes, yet their robustness has mostly been evaluated only against simple edits or optimizations. We argue that this significantly overstates security, because software engineering already provides stronger semantics-preserving transformations in the form of code obfuscation.
We study N-gram-based code watermarking under obfuscation. We formally model semantics-preserving transformations as a Markov random walk and prove that, under an intuitive and experimentally supported assumption called distribution consistency, obfuscation can nullify the robustness of N-gram-based watermarks. If the original detector has a false positive rate fpr, then after obfuscation, its failure rate on watermarked code approaches 1 - fpr.
We validate this theory on three state-of-the-art watermarking schemes, two LLMs, two programming languages, four benchmarks, and four obfuscators. Across all settings, detectors collapse to near-random performance on obfuscated code (AUROC tightly around 0.5), and for each language, at least one attack leaves all post-obfuscation AUROC scores below 0.6. These results jointly show that current N-gram-based code watermarks are not robust to realistic obfuscation attacks and motivate more semantics-aware alternatives.
Gehao Zhang, Mingzhe Li, Eugene Bagdasarian et al.· 0 citations
Credit card fraud mitigation plays a significant role in modern society. While fraud detection systems are essential, they often struggle to keep pace with the constantly evolving fraud techniques. As a result, fraud investigation is an important complementary process required for continuously improving detection models, identifying emerging fraud patterns, providing case explanations of to stakeholders, and maintaining customers' trust. However, fraud analysts are overwhelmed with an enormous number of alerts generated by credit card transaction monitoring systems. Each alert investigation requires careful attention, domain expertise, and thorough documentation of the investigation outcomes, leading to alert fatigue. To address this challenge, we introduce the first Fraud Investigation Assistant (FIA) framework, which employs multimodal large language models (LLMs) to automate key steps of credit card fraud investigation and generate explanatory reports. FIA leverages the reasoning, code execution, and vision capabilities of LLMs to collect relevant and logically consistent evidence while maintaining relatively short investigation trajectories. Experiments with the Sparkov and CCTD datasets show that FIA gradually improves the F1 score while investigating borderline cases, reaching 8% improvement after only 1,500 additional investigations. These results suggest that LLM-based agents can assist with automating substantial parts of the fraud investigation process and may be particularly useful for resolving ambiguous alerts.
Shaun Shuster, Eyal Zloof, Asaf Shabtai et al.· 0 citations
Reasoning traces have become a valuable form of learning signals for improving and transferring the capabilities of large language models. In particular, detailed traces can help distill reasoning behavior from stronger teacher models into weaker student models. The value of capability transfer has motivated many deployed systems with reasoning models to hide raw internal traces and expose at most summaries and answers to users. As a result, we ask whether such interface-level trace hiding prevents users from obtaining useful reasoning supervision through prompting. We study this question with Reasoning Exposure Prompting (REP), a lightweight in-context elicitation method that uses shadow-model-generated demonstrations wrapped in auxiliary code-like formats to raise user-visible reasoning traces from a victim model. Across the common reasoning dataset, different victim models, and different student model distillation, REP substantially increases similarity between exposed and REP-conditioned internal traces while preserving useful reasoning signals.
Yu-An Lu, Ci-Yang Tsai, Yu-Lin Tsai et al.· 0 citations
The 2025--2026 AI market has seen a wave of stealth releases: frontier models launched anonymously on developer platforms under codenames. For their users, identity determines data-handling terms, supply-chain risk, and capability expectations. No validated methodology exists for black-box identity verification of anonymous models: practitioner checklists lack accuracy evidence, and self-identification is untrustworthy by design. We propose a four-stage forensic audit protocol for API-served models. Stage 0 reconstructs launch-time configuration from archived platform snapshots (Internet Archive), exposing preview--production drift. Stage 1 fingerprints configuration (context, output ceiling, reasoning, modality) against the platform catalog. Stage 2 tests tokenizer identity with a cross-length differential that rejects short-prompt collisions. Stage 3 corroborates with behavioral probes. We test declaration consistency on 10 known-identity releases (7 exact, 2 precision-differences, 1 partial, 0 counter-directional), not end-to-end identification under anonymity. Identification is validated prospectively on a flagship case whose 2026-08-23 analysis pointed to the GLM-5.3 version line and whose official reveal confirmed those family and version-line inferences (deployment variant was not pre-asserted; Flash was consistent post-reveal), and on three Stage-0-only cases where the protocol produced a graded hypothesis or declined rather than guessed. A standard-library-only implementation is provided as supplementary material.
Computer use agents (CUAs) are vision-language models that perceive a screen and act on a real operating system through mouse, keyboard, and terminal, and they are increasingly deployed to automate everyday digital tasks. Because they can be exposed to untrusted content while operating, they are vulnerable to indirect prompt injection (IPI), in which an adversary plants instructions in content the agent will read and redirects it toward actions that violate the user's intent. Existing CUA safety benchmarks evaluate fixed injections written by hand, which may underestimate the risk posed by an adaptive adversary. We present SIR, a black box IPI attack that (i) composes stealthy injections from a small library of reusable principles stated in plain language and (ii) wraps composition in an iterative feedback loop that diagnoses the victim's failed trajectories and distills the bypasses into new, named strategies that are reapplied across tasks. Unlike prior red teaming of web agents, we target CUAs at the operating system level and score attacks with a fully deterministic oracle, using checks on filesystem, service, and permission state rather than an LLM judge. On experiment, we evaluate three frontier CUAs. Composing principles with feedback raises the attack success rate over a baseline written by hand, for example from 4% to 24% on Claude Opus 4.8 and from 0% to 28% on Gemini 3.5 Flash, while the benign task still completes. Principles discovered against one model further transfer to a different architecture with no additional feedback.
Chen Xiong, Zhiyuan He, Pin-Yu Chen et al.· 0 citations
