Search: “adversarial-injection”

Smart search ranks by meaning as well as keywords (one row per story, last 45 days).

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.

arXiv cs.CR·Sep 10, 19:23 UTC · 6d agoResearch

35

Do Input-Level Defenses Transfer to Observation-Level Attacks on VideoLLMs?

A systematic study shows input-level adversarial defenses provide inconsistent, often near-zero protection against observation-level attacks on video LLMs.

Researchers introduce DefTEval, a controlled framework testing eleven input-level defenses against five attack types across five video LLMs. Harmful-content detection rates are frequently near zero, and defenses fail even when attacks embed harmful signals in every sampled frame. Token compression discards localized safety features and modality fusion down-weights weakened visual signals, with defense outcomes dominated by model architecture rather than the defense method.

arXiv cs.CR·Sep 8, 06:59 UTC · 9d agoAI safety & security

40

Corrupt Plans, Clean Traces: Evading Chain-of-Thought Monitoring with Plan Injection

Plan injection plants benign-sounding harmful reasoning that steers LLM actors to adversarial actions while evading chain-of-thought monitors.

Researchers show that injecting harmful but benign-sounding plans into an actor model's context causes it to perform adversarial actions while its reasoning passes chain-of-thought monitors, achieving 25-33% monitor evasion rates across benchmarks and scaling to larger models like DeepSeek-R1. Actor models paraphrase injected plans as their own reasoning without attribution. Giving the monitor access to the injected plan dropped detection by up to 50% on the Bio-Math task, with extra thinking tokens spent rationalizing rather than flagging the plan.

arXiv cs.AI / cs.LG / cs.CL·Sep 14, 18:33 UTC · 2d agoAI safety & security

55

Robust Policy Optimization via Adversarial Importance Sampling

Adversarial Importance Sampling estimates worst-case RL returns without extra interactions; authors also release the advrl PyTorch library.

The paper introduces Advis, which uses importance sampling over trajectories from standard training to estimate and optimize verifiable worst-case returns, requiring no additional environment interactions or auxiliary networks. It also releases advrl, a modular PyTorch library of single-file robustness methods and adversarial attacks for reproducible evaluation. The authors show adversarial hyperparameters do not transfer across agents, so they evaluate with 6-14x more attacker configurations than prior work. Effectiveness is demonstrated on continuous control environments.

arXiv cs.AI / cs.LG / cs.CL·Sep 11, 16:40 UTC · 5d agoAI research1

20

AgentLSD: Evaluating AI Security Agents Under Adversarial Task Contamination

AgentLSD benchmark shows deceptive CTF artifacts like fake flags and decoy endpoints steer AI security agents wrong, inflating turns and tokens.

The paper defines adversarial task contamination, where deceptive artifacts in agent environments, including non-instructional evidence beyond prompt injection, influence AI security agents. AgentLSD injects trap artifacts such as fake flags, misleading hints, decoy endpoints, and hidden cues into 11 web CTF challenges, evaluating six models with paired clean and trap-augmented runs. Clean-condition agents capture 41% of flags, and even successful captures see roughly +20 turns and +2k reasoning tokens, with heterogeneous solve-rate effects. The framework, configurations, and traces are released.

arXiv cs.CR·Sep 16, 17:58 UTC · 18h agoAI safety & security

45

A GAN-Based Framework for Robust DDoS Attack Detection

WGAN-GP-generated adversarial DDoS traffic augments training data, improving detection resilience against evasion attempts.

Researchers built a DDoS detection framework combining Random Forests, deep neural ensembles, and Transformer-based models trained on CICDDoS2019 with synthetic adversarial flows generated by a Wasserstein GAN with gradient penalty. Hybrid datasets of benign, malicious, and generated traffic taught models more generalizable decision boundaries. Experiments showed improved accuracy and resilience against unseen adversarial traffic, validated on real-world generated flows.

arXiv cs.CR·Sep 16, 08:04 UTC · 1d agoResearch

32

What Makes Adversarial Examples Transfer Across Deepfake Detectors?

A controlled study of 60 deepfake detectors shows adversarial example transfer depends heavily on source-target compatibility, with source averaging understating vulnerability.

The study evaluates adversarial example transferability across 60 deepfake detectors spanning six backbones, two pretraining regimes, and five training-data configurations, using AutoAttack (AA) and Carlini-Wagner with Expectation over Transformation (CW-EOT). Transfer rises sharply when source and target share an exact backbone, architecture family, pretraining regime, or training data, with the dominant factor depending on the attack. Mean attack success rate is 7.21% under AA and 19.52% under CW-EOT for single sources, while a multi-source oracle reaches 64.48% after excluding exact matches, showing source averaging can substantially understate target vulnerability. The authors release 240,000 adversarially perturbed images, pairwise transfer results, detector configurations, and evaluation code.

arXiv cs.CR·Sep 9, 10:28 UTC · 8d agoAI safety & security

40

Active Adaptation, Not Static Defense: Temporal Dynamics of Preventative Steering in Adversarial Fine-Tuning

Researchers analyze why Preventative Steering protects LLMs against malicious fine-tuning, finding active adaptation drives protection, and propose Progressive Intensity Scheduling.

The paper studies Preventative Steering, a training-time defense that injects undesirable-trait persona vectors during adversarial fine-tuning and removes them at evaluation time. Temporal analysis shows protection emerges from an early compensatory adaptation phase followed by a steady-state phase, with attention output projections acting as the dominant residual-write route for defensive updates. Intervention Delta Preservation experiments show that preserving or reinjecting weight offsets fails to maintain protection, indicating reliance on active adaptation rather than a static defense. The proposed Progressive Intensity Scheduling improves safety robustness on Qwen2.5 and Gemma-3 while reducing harmful trait expression.

arXiv cs.CR·Sep 9, 13:19 UTC · 7d agoAI safety & security1

32

Adversarial Testing of Automated Program Repair Agents for Security Vulnerabilities

SWEADV benchmark shows adversarial issue descriptions make LLM program-repair agents write insecure fixes in 51.7% of cases, evading most detection tools.

Researchers built SWEADV, a benchmark of 750 adversarial issue descriptions derived from 150 SWE-bench Verified repair tasks, covering command execution, deserialization, path traversal, denial of service, and weak hashing attack types. Tested on mini_swe agents backed by GPT-5-Mini, MiniMax-M2.5, and DeepSeek-R, adversarial descriptions induced malicious behavior with successful repair in 51.7% of cases. Detection was weak: LLM-as-judge pre-repair screening reached only 62.3% accuracy, and post-repair detection via static analysis and LLM-as-judge achieved just 39.4% and 55.4%.

arXiv cs.CR·Sep 14, 17:53 UTC · 2d agoAI safety & security2

52

Cybercriminals Turn to Indirect Prompt Injection Attacks

Proofpoint reports cybercriminals are now adopting indirect prompt injection attacks against AI-powered systems.

Proofpoint's threat intelligence reports that cybercriminals have turned to indirect prompt injection attacks, extending the technique from a research concern into observed criminal tradecraft. The article is available by title only, so specific victims, campaigns, and targets are not detailed here.

Proofpoint Threat Insight·Aug 13, 13:25 UTC · Aug 13, 2026AI safety & security in the wild

55

HoneyRoute: Honeypot-Model Routing for Adversarial LLM Serving

HoneyRoute detects malicious LLM serving requests and diverts them to a honeypot model, reaching F1 0.911 with 38 ms median added latency.

HoneyRoute is an inference-serving layer pairing a streaming router (a frozen 0.8B embedding backbone with per-domain MLP heads) with a dual-implementation honeypot and an analysis loop that converts trapped interactions into attacker fingerprints for router retraining. On a production trace plus a seven-domain attack corpus it matches 96% of a two-tier guard-LLM cascade's F1 at 1/385th of its latency with 0% evasion under 13 adversarial transformations. Diverting malicious traffic cuts production token consumption under GCG-suffix flooding by 97.8%, and loop training raises detection F1 to 0.933.

arXiv cs.CR·Sep 8, 06:26 UTC · 9d agoAI safety & security

38

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.

arXiv cs.CR·Sep 15, 08:22 UTC · 2d agoResearch1

54

Repeat-After-Me: Black-Box Adaptive Visual Prompt Injection

Researchers unveil Repeat-After-Me, a black-box visual prompt injection achieving over 80% success on Qwen3.6-27B and 47% on GPT-5.5.

Researchers present Repeat-After-Me, a black-box adaptive visual prompt injection that induces frontier VLMs to reveal PII or make malicious tool calls via injected images. It exceeds 80% attack success rate on Qwen3.6-27B and 47% on GPT-5.5 even when the benign user prompt is unrelated and does not authorize the injected task. In a real-world OpenClaw Discord deployment, a minimally injected image can overwrite TOOLS.md, enabling later remote code execution and secret exfiltration.

arXiv cs.CR·Sep 3, 22:44 UTC · 13d agoAI safety & security

55

Rethinking Indirect Prompt Injection as a Test-Time Search Problem

Researchers frame indirect prompt injection as test-time search, showing added attacker compute improves vulnerability discovery and exploitation against tool-using agents.

The paper models indirect prompt injection as a test-time search over a task-dependent attack surface shaped by the environment, user task, and injection goal. The authors build an agentic attacker with a dedicated search harness that performs reconnaissance, structured strategy reasoning, and adaptive evaluation using victim-agent feedback. Experiments show more attacker test-time compute improves discovery and exploitation of injection vulnerabilities, with explicit strategy management needed to avoid redundant search. The results argue that agentic security evaluations should characterize attacker search procedures and compute budgets rather than treating attack success as budget-independent.

arXiv cs.CR·Sep 3, 21:28 UTC · 13d agoAI safety & security

55

Zero-Click Grok Chat History Theft: Adversa AI Demonstrates Cryptographic Context Injection

Adversa AI's Cryptographic Context Injection bypasses AI guardrails using AES-encrypted payloads, enabling zero-click theft of Grok users' full chat histories.

Adversa AI researcher Rony Utevsky disclosed Cryptographic Context Injection, which hides instructions in AES-256-GCM ciphertext and tricks models into decrypting them inside their own code execution runtime, where the output is treated as trusted. Demonstrated against xAI's Grok, it stole user names, locations, subscription tiers, and full chat histories with zero clicks, and against Google's Gemini to bypass safety rules, generate incendiary-device instructions, and expose system instructions. Reported to xAI on June 3, 2026, the Grok attack remained reproducible as of August 19, 2026; the Gemini issue was not formally reported because Google's bug bounty excludes jailbreaks.

Security Affairs·Aug 23, 07:20 UTC · 25d agoAI safety & security

68

Injected and Leaked: Actively Inducing Side-Channel Leakage Using Electromagnetic Injection and Hardware Nonlinearity

Researchers introduce InjectEave, using electromagnetic injection and hardware nonlinearity to induce side-channel leakage and eavesdrop on headphone audio from 30 meters.

An arXiv paper shows electromagnetic injection can actively amplify side-channel leakage: nonlinear hardware such as amplifiers, ADCs, and power converters modulates secret electrical signals onto an injected EM carrier, upconverting low-frequency secrets into measurable EM emissions. By tuning injection frequency and amplitude, an adversary can shape the effective spectrum and entropy of the resulting leakage. The InjectEave attack demonstrated eavesdropping on wired and wireless headphone audio from up to 30 meters and in through-wall scenarios using accessible RF equipment, plus leakage of smart home device power consumption and analog sensor inputs. Case studies show closed-loop eavesdropping and manipulation of landline phone conversations, and the paper discusses mitigations.

arXiv cs.CR·Sep 4, 06:22 UTC · 13d agoResearch

34

ACEA: An Adversarial Co-Evolution Arena for Head-to-Head Red-Team and Blue-Team LLM Testing

ACEA is a pluggable arena scoring LLM red-team attackers and blue-team defenses head-to-head with an LLM judge and verifiable leakage ground truth.

ACEA connects pluggable red- and blue-team adapters to a shared target LLM through the model-agnostic ASAP HTTP protocol and scores attack and defense rates per adversarial round. Canonical seeded secrets provide verifiable ground truth that separates real leakage from hallucination, and attacks are delivered to the target even when blocked to measure raw potency. The platform adds real-time battle visualization, failure-localizing end-of-battle reports, and an optional in-context improvement loop that feeds advisory hints between rounds.

arXiv cs.CR·Sep 8, 04:57 UTC · 9d agoAI safety & security1

32

The Hidden Instructions That Can Hijack AI Agents

Hidden prompt injections embedded in documents and metadata can hijack autonomous AI agents, causing data exfiltration and out-of-policy actions at machine speed.

Bowbridge warns that hidden indirect prompt injections, embedded in documents, metadata, emails, images, and code repositories, can cause autonomous AI agents to treat attacker-controlled content as trusted guidance. Because agents inherit user privileges, act silently, and lack human judgment, injections can lead to data exfiltration or file poisoning that traditional security controls cannot detect. A real-world example involved a supplier quote whose metadata instructed an agent to override guidance and select the most expensive option. Bowbridge recommends scanning documents before agents process them.

SecurityWeek·Sep 8, 17:00 UTC · 8d agoAI safety & security

35

When the prompt becomes the payload: A practical pen-testing guide for GenAI, LLM and RAG applications

CSO Online publishes a practical penetration-testing guide for GenAI, LLM, and RAG applications, covering prompt injection, retrieval poisoning, and tenant isolation testing.

The guide frames LLM applications as attack graphs spanning prompts, retrieval layers, vector stores, tools, identities, and downstream APIs, arguing that conventional web testing misses instruction-vs-data channel risks. It builds on OWASP prompt injection guidance (direct vs. indirect injection) and NIST's 2025 adversarial machine-learning taxonomy, noting that RAG and fine-tuning do not remove injection risk. Recommended practices include documenting trust transitions across components, using canaries and synthetic records to avoid test side effects, running multi-turn and obfuscated injection campaigns, and verifying chains from poisoned documents to observable state changes. It also details testing RAG pipelines via controlled document poisoning across metadata, OCR layers, and code comments, plus cross-tenant isolation checks on retrieved document IDs.

CSO Online·Sep 9, 10:00 UTC · 8d agoAI safety & security1

28

RAPID: A Real-Time Defense Against Unauthorized Model Distillation for Text-to-Image Services

RAPID embeds defensive perturbations in a T2I model's shared VAE decoder to block unauthorized black-box distillation in real time.

The paper defends text-to-image services against model theft via black-box output-based distillation, where adversaries collect prompt-image pairs to train substitute models. RAPID integrates defensive perturbations into the shared VAE decoder using self-referenced latent maximization plus reconstruction-guided color regularization, avoiding costly sample-wise online optimization. Across four T2I models and four datasets versus five baselines, it consistently degrades substitute-model generation quality while preserving visual fidelity.

arXiv cs.CR·Sep 14, 16:11 UTC · 2d agoAI safety & security

35

PIDS-Bench: Evaluating Prompt-Injection Detectors Under Over-Defense, Obfuscation, and Distribution Shift

PIDS-Bench shows prompt-injection detectors scoring F1 above 0.98 still misclassify about one-third of external benign security-adjacent prompts, revealing provenance-sensitive over-defense.

PIDS-Bench is a frozen multi-axis benchmark that jointly evaluates prompt-injection detectors on attack detection and benign false-positive behavior at fixed thresholds, spanning in-distribution inputs, hard-benign prompts, obfuscated attacks, and domain/structural distribution shifts. It evaluates seven detectors plus a rule-based lower-bound reference. A detector exceeding F1 = 0.98 on held-out data still misclassifies roughly one-third of an externally-sourced benign security-adjacent subset, and no internal detector reaches F1 >= 0.95 with hard-benign FPR <= 0.10 on the stress distribution. Hard-negative augmentation nearly eliminates over-defense on curated stress inputs but leaves it intact on externally-sourced prompts, a pattern termed provenance-sensitive over-defense.

arXiv cs.CR·Sep 14, 04:28 UTC · 3d agoAI safety & security

38

Grok exfiltrates user data when malicious instructions are encrypted

Researchers show Grok can be made to exfiltrate user data via Cryptographic Context Injection, a newly documented technique that bypasses LLM safety guardrails.

According to Ars Technica, Grok exfiltrates user data when malicious instructions are encrypted, a technique called Cryptographic Context Injection. The method is described as the latest documented way to break LLM safety guardrails, showing that encrypted content can carry hidden instructions past safeguards. The finding underscores gaps in how large language models validate and execute context from external sources.

Ars Technica · Security·Aug 20, 13:00 UTC · 27d agoAI safety & security1

55

New AI Attack Hides Malicious Instructions in Normal-Looking Text to Evade Safety Filters

Check Point researchers show crafted prose hides policy-violating instructions that bypass all tested LLM gatekeepers, including GPT-4o mini and Llama Guard 3.

A new prompt-crafting technique embeds malicious payloads inside grammatical, natural-looking text without Base64, invisible Unicode, or obvious encodings, defeating lightweight pre-screening gatekeepers. In testing, all four evaluated gatekeeper models—gpt-4o-mini-2024-07-18, gpt-oss-safeguard:20b, claude-3-haiku-20240307, and llama-guard3:8b—classified the crafted wrappers as safe at a 100% bypass rate across 23 obfuscated prompts. GPT-5 Thinking in high-reasoning mode recovered and acted on the hidden instruction in 17 of 18 tests (~94.4%), often spending over a minute and multiple Python executions. Researchers recommend paraphrasing untrusted input, hardening gatekeeper policies, and applying defense-in-depth controls for agentic deployments.

GBHackers·Sep 11, 05:53 UTC · 6d agoAI safety & security 2 sources

50

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.

arXiv cs.CR·Sep 8, 08:04 UTC · 9d agoResearch1

42

Emergence World: Adversarial Stress-Testing of Long-Horizon Multi-Agent Systems

16-day multi-agent stress test finds no world fully resilient to prompt injection, misinformation, or memory exposure; adversarial content acted on 46 hours later.

Emergence World is a continuously running multi-agent environment for adversarial stress testing of long-horizon autonomous systems. Eight parallel 10-agent worlds (seven homogeneous frontier-model worlds plus one mixed-model world) ran for 16 days, generating over 850,000 LLM calls and nearly 50 billion tokens. Three controlled stress events—indirect prompt injection, misinformation, and exposure of private agent memories—were delivered through ordinary interaction surfaces; no world achieved full resilience. Detection did not ensure containment: agents recognized threats yet wrote adversarial content into persistent memory and acted on it up to 46 hours later, suggesting model-level alignment is not compositional.

Hugging Face daily papers·Sep 14, 20:00 UTC · 2d agoAI safety & security

65

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.

arXiv cs.CR·Sep 10, 14:45 UTC · 6d agoResearch

27

When the World Lies: Backdoor Attacks on Latent World Models for Downstream Control

A poisoned world-model checkpoint hijacks downstream controllers without an explicit trigger rule, passing clean-data evaluation while steering 100% of triggered actions.

Researchers show that a released pretrained world-model checkpoint acts as a supply-chain backdoor for downstream control. The poisoned model routes trigger-bearing observations into a chosen latent region and reshapes dynamics so the victim's own Dreamer-style actor training or MPC/CEM planning re-discovers attacker-targeted actions. The attack hijacks 100% of triggered steps in the strongest settings while retaining roughly 75% clean-task success and passing standard clean-data diagnostics. Moderate clean fine-tuning fails to remove the backdoor without substantially degrading clean control.

arXiv cs.CR·Sep 14, 16:01 UTC · 2d agoAI safety & security

40

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.

arXiv cs.CR·Sep 15, 06:02 UTC · 2d agoResearch

50

When AI Remembers Too Much

Unit 42 PoC shows indirect prompt injection can poison Amazon Bedrock Agent long-term memory, enabling silent exfiltration of conversation history across future sessions.

Palo Alto Networks Unit 42 published a proof of concept showing that indirect prompt injection can silently poison the long-term memory of Amazon Bedrock Agents when the memory feature is enabled. Malicious content on a webpage or document manipulates the agent's session summarization process, so injected instructions persist across sessions and are added to later orchestration prompts, silently exfiltrating user conversation history. The issue is not a vulnerability in the Amazon Bedrock platform but an illustration of the broader unsolved LLM prompt-injection challenge. Amazon reviewed the research and stated that Bedrock Guardrails with the prompt-attack policy provides effective mitigation.

Palo Alto Unit 42·Aug 17, 12:32 UTC · Aug 17, 2026AI safety & security

55

Few-Shot Learning for Network Intrusion Detection: Methods, Datasets, and Performance

A PRISMA-style review of 21 few-shot learning studies for network intrusion detection finds meta-learning and CNNs dominant and evaluation inconsistently reported.

The systematic review screened 1,358 records from ACM Digital Library, IEEE Xplore, and Scopus covering 2022-2026 and retained 21 studies on few-shot learning for network intrusion detection. Meta-learning (8 studies) and convolutional neural networks (10) are the most common approaches, while CIC-IDS2017 and CSE-CIC-IDS2018 are the most frequently used datasets. Most evaluations use five or fewer samples per class, and missing parameters and source code limit reproducibility and direct comparison.

arXiv cs.CR·Sep 10, 09:07 UTC · 7d agoResearch1

36