Rapid Poison: Practical Poisoning Attacks Against the Rapid Response Framework

• URL: http://arxiv.org/abs/2606.16242v1
• Date: Mon, 15 Jun 2026 05:40:50 GMT
• Title: Rapid Poison: Practical Poisoning Attacks Against the Rapid Response Framework
• Abstract summary: We show that prompt injection can infiltrate the pipeline to deliver poisoned samples into the training set.<n>We address this with Omission Attack, which exploits a new phenomenon: when training on concept-absent unsafe samples, the classifier misassociates that concept's presence with the safe label.
• Score: 38.96400184175405
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The Rapid Response (RR) framework, deployed in production systems, including Anthropic's ASL-3 safeguards, continuously improves jailbreak-detection classifiers. When new jailbreaks emerge that bypass these classifiers, Rapid Response generates synthetic variants for training, helping the model generalize from the new attacks and quickly adapt. We reveal that prompt injection can infiltrate this pipeline to deliver poisoned samples into the classifier's training set, enabling two attack objectives: (I) targeted poisoning attacks that create false positives on harmless samples by categorizing them as a jailbreak, with a specific desired feature (e.g., certain formatting, subject, or keyword), (II) concept-based backdoor attacks that induce false negatives on jailbreak inputs, generalizing even to jailbreaks from attack strategies the defender explicitly trained against, when the backdoor trigger is present. Importantly, our threat model restricts adversaries to modifying only jailbreak samples (not benign data or labels), a constraint unexplored by prior work that makes the second objective particularly challenging. We address this with Omission Attack, which exploits a new phenomenon: when training on concept-absent unsafe samples, the classifier misassociates that concept's presence with the safe label. Both attacks cause substantial and in some cases near-complete label flipping at only a 1% poisoning rate, achieving up to 100% false positive rates and up to 96% false negative rates.

Related papers

• Analyzing Defensive Misdirection Against Model-Guided Automated Attacks on Agentic AI Systems [0.0]
  Agentic AI systems increasingly rely on language-model components to interpret instructions, process external data, invoke tools, and coordinate with other agents.<n>This work analyzes the resulting attack-defense setting through a probabilistic model of a target system, its defense mechanism, and the attacker's automated judge.
  arXiv  Detail & Related papers  (2026-06-18T16:50:28Z)
• Adversarial Déjà Vu: Jailbreak Dictionary Learning for Stronger Generalization to Unseen Attacks [57.08407099520887]
  Defending against novel jailbreaks represents a critical challenge in AI safety.<n>This paper proposes a new paradigm for improving robustness against unseen jailbreaks.
  arXiv  Detail & Related papers  (2025-10-24T17:37:25Z)
• 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)
• Layer-Level Self-Exposure and Patch: Affirmative Token Mitigation for Jailbreak Attack Defense [55.77152277982117]
  We introduce Layer-AdvPatcher, a methodology designed to defend against jailbreak attacks.<n>We use an unlearning strategy to patch specific layers within large language models through self-augmented datasets.<n>Our framework reduces the harmfulness and attack success rate of jailbreak attacks.
  arXiv  Detail & Related papers  (2025-01-05T19:06:03Z)
• SEEP: Training Dynamics Grounds Latent Representation Search for Mitigating Backdoor Poisoning Attacks [53.28390057407576]
  Modern NLP models are often trained on public datasets drawn from diverse sources. Data poisoning attacks can manipulate the model's behavior in ways engineered by the attacker. Several strategies have been proposed to mitigate the risks associated with backdoor attacks.
  arXiv  Detail & Related papers  (2024-05-19T14:50:09Z)
• AutoDAN: Interpretable Gradient-Based Adversarial Attacks on Large Language Models [55.748851471119906]
  Safety alignment of Large Language Models (LLMs) can be compromised with manual jailbreak attacks and (automatic) adversarial attacks. Recent studies suggest that defending against these attacks is possible: adversarial attacks generate unlimited but unreadable gibberish prompts, detectable by perplexity-based filters. We introduce AutoDAN, an interpretable, gradient-based adversarial attack that merges the strengths of both attack types.
  arXiv  Detail & Related papers  (2023-10-23T17:46:07Z)

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.