Pith. sign in

REVIEW 5 cited by

Hijacking Large Language Models via Adversarial In-Context Learning

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2311.09948 v3 pith:ESPUVMQI submitted 2023-11-16 cs.LG cs.CLcs.CR

classification cs.LGcs.CLcs.CR
keywords llmsadversarialdemosin-contextpromptattackattacksdefense
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
read the original abstract

In-context learning (ICL) has emerged as a powerful paradigm leveraging LLMs for specific downstream tasks by utilizing labeled examples as demonstrations (demos) in the preconditioned prompts. Despite its promising performance, crafted adversarial attacks pose a notable threat to the robustness of LLMs. Existing attacks are either easy to detect, require a trigger in user input, or lack specificity towards ICL. To address these issues, this work introduces a novel transferable prompt injection attack against ICL, aiming to hijack LLMs to generate the target output or elicit harmful responses. In our threat model, the hacker acts as a model publisher who leverages a gradient-based prompt search method to learn and append imperceptible adversarial suffixes to the in-context demos via prompt injection. We also propose effective defense strategies using a few shots of clean demos, enhancing the robustness of LLMs during ICL. Extensive experimental results across various classification and jailbreak tasks demonstrate the effectiveness of the proposed attack and defense strategies. This work highlights the significant security vulnerabilities of LLMs during ICL and underscores the need for further in-depth studies.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 5 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. How Can Mamba Learn In Context with Outliers and Generalize Provably?

    cs.LG 2025-10 conditional novelty 6.0 of 10

    A simplified one-layer Mamba provably learns in-context binary classification tolerating outlier fractions approaching 1, whereas a linear Transformer can only tolerate α < 1/2.

  2. Automatic Calibration for Membership Inference Attack on Large Language Models

    cs.LG 2025-05 conditional novelty 6.0 of 10

    A temperature-calibrated scoring method, ACMIA, improves membership inference against LLMs by amplifying probability gaps between training and non-training texts without reference models.

  3. Layer-Wise Perturbations via Sparse Autoencoders for Adversarial Text Generation

    cs.CL 2025-08 reject novelty 5.0 of 10

    Sparse autoencoder activation perturbation (SFPF) applied on top of existing jailbreak prompts raises attack success rate on Qwen3-32B, but with no defense evaluation and weak reproducibility.

  4. Security Concerns for Large Language Models: A Survey

    cs.CR 2025-05 conditional novelty 5.0 of 10

    A survey that classifies LLM security threats and argues that intrinsic agentic risks, such as scheming, are underappreciated and poorly defended.

  5. Navigating the Risks: A Survey of Security, Privacy, and Ethics Threats in LLM-Based Agents

    cs.AI 2024-11 conditional novelty 4.0 of 10

    A survey proposing a source-and-impact taxonomy (input, model, combined; security, privacy, ethics) for threats to LLM-based agents, with feature analysis and four case studies.

Pith tools