Pith. sign in

REVIEW 21 cited by

Automatic and Universal Prompt Injection Attacks against Large Language Models

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 2403.04957 v1 pith:Y43GHIV4 submitted 2024-03-07 cs.AI

Automatic and Universal Prompt Injection Attacks against Large Language Models

classification cs.AI
keywords attacksinjectionpromptlanguagedatageneratinggradient-basedlarge
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

Large Language Models (LLMs) excel in processing and generating human language, powered by their ability to interpret and follow instructions. However, their capabilities can be exploited through prompt injection attacks. These attacks manipulate LLM-integrated applications into producing responses aligned with the attacker's injected content, deviating from the user's actual requests. The substantial risks posed by these attacks underscore the need for a thorough understanding of the threats. Yet, research in this area faces challenges due to the lack of a unified goal for such attacks and their reliance on manually crafted prompts, complicating comprehensive assessments of prompt injection robustness. We introduce a unified framework for understanding the objectives of prompt injection attacks and present an automated gradient-based method for generating highly effective and universal prompt injection data, even in the face of defensive measures. With only five training samples (0.3% relative to the test data), our attack can achieve superior performance compared with baselines. Our findings emphasize the importance of gradient-based testing, which can avoid overestimation of robustness, especially for defense mechanisms.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 21 Pith papers

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

  1. Measuring Real-World Prompt Injection Attacks in LLM-based Resume Screening

    cs.CR 2026-05 unverdicted novelty 8.0

    Roughly 1% of real resumes contain hidden prompt injections against LLM screeners, prevalence has risen over 1-2 years, and over 90% avoid explicit instructions.

  2. Prompt Infection: LLM-to-LLM Prompt Injection within Multi-Agent Systems

    cs.MA 2024-10 unverdicted novelty 8.0

    Prompt injection attacks can self-replicate across LLM agents in multi-agent systems, enabling data theft, misinformation, and system disruption while propagating silently.

  3. Prompt Injection in Automated R\'esum\'e Screening with Large Language Models: Single and Multi-Injection Settings

    cs.AI 2026-06 unverdicted novelty 7.0

    Experiments show prompt injection boosts resume rankings in LLM screening when rare and qualities homogeneous, but fails when common or qualities differ.

  4. AutoDojo: Adaptive Black-Box Attacks Reveal the Limits of IPI Defenses and Task-Specification Effects in LLM Agents

    cs.CR 2026-06 unverdicted novelty 7.0

    AutoDojo adaptively optimizes IPI attacks to bypass defenses, recovering substantial ASR on action-open tasks where static attacks fail.

  5. A Cross-Modal Prompt Injection Attack against Large Vision-Language Models with Image-Only Perturbation

    cs.CR 2026-05 unverdicted novelty 7.0

    CrossMPI steers both visual and textual interpretations in LVLMs through image-only perturbations by optimizing in hidden-state space at selected middle layers with distance-based budget allocation.

  6. FlowSteer: Prompt-Only Workflow Steering Exposes Planning-Time Vulnerabilities in Multi-Agent LLM Systems

    cs.CR 2026-05 unverdicted novelty 7.0

    FlowSteer is a prompt-only attack that biases multi-agent LLM workflow planning to propagate malicious signals, raising success rates by up to 55%, with FlowGuard as an input-side defense reducing it by up to 34%.

  7. AgentVisor: Defending LLM Agents Against Prompt Injection via Semantic Virtualization

    cs.CR 2026-04 unverdicted novelty 7.0

    AgentVisor cuts prompt injection success rate to 0.65% in LLM agents with only 1.45% utility loss via semantic privilege separation and one-shot self-correction.

  8. From Neural Intent to Cryptographic Authorization: Securing AI-Driven Enterprise Workflows

    cs.CR 2026-07 conditional novelty 6.0

    NCS gates every privileged AI-agent tool call behind an offline-signed, hash-chained instruction stream, cutting injected-parameter attacks to zero by construction.

  9. PI-Hunter: Automated Red-Teaming for Exposing and Localizing Prompt Injections

    cs.CR 2026-06 unverdicted novelty 6.0

    PI-Hunter automates red-teaming of LLM agents by generating and iteratively evolving source-aware test cases to induce retrieval of embedded malicious instructions from external environments.

  10. Aligning Provenance with Authorization: A Dual-Graph Defense for LLM Agents

    cs.CR 2026-05 unverdicted novelty 6.0

    AuthGraph aligns an execution provenance graph with a clean authorization graph to detect parameter-source deviations from user intent, reducing attack success rates to 1-2% on AgentDojo and AgentDyn while retaining m...

  11. LoopTrap: Termination Poisoning Attacks on LLM Agents

    cs.CR 2026-05 unverdicted novelty 6.0

    LoopTrap is an automated red-teaming framework that crafts termination-poisoning prompts to amplify LLM agent steps by 3.57x on average (up to 25x) across 8 agents.

  12. FlashRT: Towards Computationally and Memory Efficient Red-Teaming for Prompt Injection and Knowledge Corruption

    cs.CR 2026-04 unverdicted novelty 6.0

    FlashRT delivers 2x-7x speedup and 2x-4x GPU memory reduction for prompt injection and knowledge corruption attacks on long-context LLMs versus nanoGCG.

  13. From Rookie to Expert: Manipulating LLMs for Automated Vulnerability Exploitation in Enterprise Software

    cs.SE 2025-12 unverdicted novelty 6.0

    RSA prompting enables LLMs to automatically create functional exploits for CVEs in Odoo ERP, succeeding on all tested cases in 3-5 rounds and removing the need for manual effort.

  14. Optimus: A Robust Defense Framework for Mitigating Toxicity while Fine-Tuning Conversational AI

    cs.CR 2025-07 unverdicted novelty 6.0

    Optimus mitigates toxicity during LLM fine-tuning by combining repurposed LLM safety alignments for detection with synthetic data and DPO alignment, remaining effective even with highly biased classifiers and against attacks.

  15. Robustness via Referencing: Defending against Prompt Injection Attacks by Referencing the Executed Instruction

    cs.CR 2025-04 unverdicted novelty 6.0

    The method prompts LLMs to output both answers and references to the executed instructions, then filters out any answers not linked to the original input instructions, reducing attack success rates to zero in tested s...

  16. Progent: Securing AI Agents with Privilege Control

    cs.CR 2025-04 unverdicted novelty 6.0

    Progent introduces a privilege-control framework for AI agents that uses LLM-generated symbolic rules over tools, SMT-solver-enforced monotonic updates, and deterministic checks to reduce attack success rates on Agent...

  17. The safety failures we are not instrumenting: a perspective on hidden safety-critical challenges in modern AI systems

    cs.CY 2026-07 conditional novelty 5.0

    AI safety should be measured by whether deployed systems keep errors visible, contestable, containable, and recoverable across five integrity layers, not only by whether individual model outputs look safe.

  18. Devil in the Lens: Analyzing and Defending Physical Prompt Injection Against Vision-Language Models on Wearable Devices

    cs.CR 2026-07 conditional novelty 5.0

    Physical scene text can inject prompts into wearable VLMs, hijacking decisions and content with high success rates across six threat scenarios, partially mitigated by OCR masking and token-drift defenses.

  19. SoK: Security of Autonomous LLM Agents in Agentic Commerce

    cs.CR 2026-04 unverdicted novelty 5.0

    The paper systematizes security for LLM agents in agentic commerce into five threat dimensions, identifies 12 cross-layer attack vectors, and proposes a layered defense architecture.

  20. Agentic AI Security: Threats, Defenses, Evaluation, and Open Challenges

    cs.AI 2025-10 unverdicted novelty 4.0

    A survey that taxonomizes threats to agentic AI, reviews benchmarks and evaluation methods, discusses technical and governance defenses, and identifies open challenges.

  21. Safety at Scale: A Comprehensive Survey of Large Model and Agent Safety

    cs.CR 2025-02 unverdicted novelty 2.0

    A comprehensive survey that taxonomizes safety threats to large models and agents, reviews defenses and benchmarks, and outlines open challenges.