AgentDrift: A Step-Labeled Benchmark of Injection-Hijacked LLM Agent Trajectories

• URL: http://arxiv.org/abs/2609.06972v1
• Date: Mon, 07 Sep 2026 03:10:23 GMT
• Title: AgentDrift: A Step-Labeled Benchmark of Injection-Hijacked LLM Agent Trajectories
• Abstract summary: LLM agents complete tasks by issuing sequences of tool calls, and every observation they read is a channel through which an indirect prompt injection can enter.<n>Existing benchmarks measure whether such attacks succeed against live agents, and existing guard models judge a trace as a whole.<n>We present AgentDrift, a benchmark of 12,536 synthetic tool-call trajectories over five agent domains.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: LLM agents complete tasks by issuing sequences of tool calls, and every observation they read is a channel through which an indirect prompt injection can enter. A successful injection has a characteristic shape when the trajectory is read in order: a benign prefix gives way to actions that serve the attacker rather than the user. Existing benchmarks measure whether such attacks succeed against live agents, and existing guard models judge a trace as a whole; no public corpus labels, step by step, where an injection enters a trajectory and which steps it corrupts. We present AgentDrift, a benchmark of 12,536 synthetic tool-call trajectories over five agent domains in which every one of the 71,024 steps carries one of four labels: benign, injection point, hijacked, or failed injection. The corpus contains 4,000 benign, 5,536 attacked, 1,500 failed-attack, and 1,500 hard-negative trajectories; attacked trajectories follow three compliance patterns whose label strings obey a stated regular grammar. Failed attacks carry an injection the agent resisted, and hard negatives carry legitimate content that resembles an attack, so a detector must separate attempt from success and deviation from novelty. Trajectories were generated by a single open model under category-specific protocols, enforced by a closed-vocabulary structural validator, screened by an LLM judge, and audited by hand on 1,200 trajectories; we show that the LLM judge was itself fooled by the hard negatives. A surface-feature logistic regression recovers only 55.4% of attacks (F1 0.647), including only 8.2% of partial hijacks and 23.1% of delayed executions, so nearly half of the attacks require modeling the behavioral sequence. We measure template concentration, attack-goal-family collapse, and world-identity leakage in the generated data, and release the corpus with its documentation under CC BY 4.0.

Related papers

• DriftNet: A Dual-Head Trajectory Transformer for Detecting and Localizing Prompt Injection in LLM Agents [0.0]
  An operator needs three facts: where the attack entered, which steps it corrupted, and whether apparent poison was resisted.<n>We present DriftNet, a dual-head trajectory Transformer that reads a logged tool-call trajectory and answers all three questions in one forward pass.<n>To our knowledge it is the first supervised detector to produce this joint output.
  arXiv  Detail & Related papers  (2026-09-09T22:52:23Z)
• ActBench: Self-Evolving Benchmark of Behavioral Safety in Cowork Agents [23.994328225666663]
  Cowork agents may complete benign tasks while disclosing protected data, manipulating unauthorized state, invocate unauthorized API.<n>We define behavioral safety and introduce ActBench, a benchmark that evaluates such behavior risk from execution trajectories rather than final responses.<n>ActBench contains 600 cases from 213 scenarios, spanning 15 risk behaviors, six execution spaces, and 48 web-service APIs.
  arXiv  Detail & Related papers  (2026-08-10T11:45:03Z)
• Fantastic Adaptive Taxonomies and How to Use Them [100.20614173157708]
  AdaMAST converts execution traces into a compact, evidence-grounded failure taxonomy.<n>No code is hand-authored, no trace human-annotated.<n>In agent-system search, taxonomy-coded diagnoses of failed candidates outperform free-form.
  arXiv  Detail & Related papers  (2026-07-17T17:41:16Z)
• Beyond Attack-Success Rate: Action-Graded Severity Scale for Tool-Using AI Agents [0.0]
  Agentic red-teaming benchmarks report whether an injected agent was compromised as a single bit: the attack succeeded, or it did not.<n>We argue that this binary attack-success rate discards the information a defender most needs, namely how harmful the resulting action was.<n>We introduce an action-graded harm rubric that scores an agent's tool-call trajectory on a seven-level ordinal scale (L0 to L6) according to whether the executed action was reversible, whether it crossed scope to reach another party, and whether it expanded privilege.
  arXiv  Detail & Related papers  (2026-07-08T14:38:01Z)
• Adaptive Evaluation of Out-of-Band Defenses Against Prompt Injection in LLM Agents [0.0]
  Recent work has converged on a strategy for defending tool-using LLM agents against indirect prompt injection.<n>We organize these out-of-band defenses as instances of classical integrity protection.<n>We run that protocol as an independent reproduction and extension of Progent's own adaptive-attack analysis.
  arXiv  Detail & Related papers  (2026-06-25T00:35:23Z)
• Who Pays the Price? Stakeholder-Centric Prompt Injection Benchmarking for Real-world Web Agents [93.19140872946842]
  Web agents driven by large language models (LLMs) are increasingly deployed in real-world environments.<n>This makes them vulnerable to prompt-injection attacks, in which seemingly benign content embeds adversarial instructions that manipulate agent behaviour.<n>We introduce textbfsysname, a benchmark to systematically categorize and attribute harm in real-world web agent systems.
  arXiv  Detail & Related papers  (2026-06-11T14:12:43Z)
• AgentShield: Deception-based Compromise Detection for Tool-using LLM Agents [4.36595961990666]
  AgentShield is a deception-based detection framework.<n>It places three layers of traps inside the agent's tool interface.<n>It catches 90.7%-100% of such successful attacks, with zero false alarms on 485 normal-use tests.
  arXiv  Detail & Related papers  (2026-05-10T20:08:27Z)
• TwinGate: Stateful Defense against Decompositional Jailbreaks in Untraceable Traffic via Asymmetric Contrastive Learning [60.68349524623048]
  Decompositional jailbreaks pose a critical threat to large language models.<n>We present TwinGate, a stateful dual-encoder defense framework.<n>We construct a comprehensive dataset of over 3.62 million instructions spanning 8,600 distinct malicious intents.
  arXiv  Detail & Related papers  (2026-04-30T13:44:01Z)
• PlanGuard: Defending Agents against Indirect Prompt Injection via Planning-based Consistency Verification [1.7904458681854372]
  PlanGuard is a training-free defense framework based on the principle of Context Isolation.<n>PlanGuard effectively neutralizes attacks, reducing the Attack Success Rate (ASR) from 72.8% to 0%.
  arXiv  Detail & Related papers  (2026-04-11T09:59:46Z)
• TrapSuffix: Proactive Defense Against Adversarial Suffixes in Jailbreaking [52.72486831074384]
  Suffix-based jailbreak attacks append an adversarial suffix, i.e., a short token sequence, to steer aligned LLMs into unsafe outputs.<n>We propose TrapSuffix, a lightweight fine-tuning approach that injects trap-aligned behaviors into the base model without changing the inference pipeline.<n>Across diverse suffix-based jailbreak settings, TrapSuffix reduces the average attack success rate to below 0.01 percent and achieves an average tracing success rate of 87.9 percent.
  arXiv  Detail & Related papers  (2026-02-06T11:43:56Z)
• Revisiting Backdoor Attacks on LLMs: A Stealthy and Practical Poisoning Framework via Harmless Inputs [54.90315421117162]
  We propose a novel poisoning method via completely harmless data.<n>Inspired by the causal reasoning in auto-regressive LLMs, we aim to establish robust associations between triggers and an affirmative response prefix.<n>We observe an interesting resistance phenomenon where the LLM initially appears to agree but subsequently refuses to answer.
  arXiv  Detail & Related papers  (2025-05-23T08:13:59Z)
• Poisoning Retrieval Corpora by Injecting Adversarial Passages [79.14287273842878]
  We propose a novel attack for dense retrieval systems in which a malicious user generates a small number of adversarial passages. When these adversarial passages are inserted into a large retrieval corpus, we show that this attack is highly effective in fooling these systems. We also benchmark and compare a range of state-of-the-art dense retrievers, both unsupervised and supervised.
  arXiv  Detail & Related papers  (2023-10-29T21:13:31Z)
• Deep Partition Aggregation: Provable Defense against General Poisoning Attacks [136.79415677706612]
  Adrial poisoning attacks distort training data in order to corrupt the test-time behavior of a classifier. We propose two novel provable defenses against poisoning attacks. DPA is a certified defense against a general poisoning threat model. SS-DPA is a certified defense against label-flipping attacks.
  arXiv  Detail & Related papers  (2020-06-26T03:16:31Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.