mlsanityData to 7 Oct 2026

ShallowJail: Steering Jailbreaks against Large Language Models

arXiv 2602.07107 ↗First posted 6 Feb 2026cs.CR cs.AIcited by 1

On the map: LLM safety and security → Jailbreaking

Abstract (arXiv)

Large Language Models(LLMs) have been successful in numerous fields. Alignment has usually been applied to prevent them from harmful purposes. However, aligned LLMs remain vulnerable to jailbreak attacks that deliberately mislead them into producing harmful outputs. Existing jailbreaks are either black-box, using carefully crafted, unstealthy prompts, or white-box, requiring resource-intensive computation. In light of these challenges, we introduce ShallowJail, a novel attack that exploits shallow alignment in LLMs. ShallowJail can misguide LLMs' responses by manipulating the initial tokens during inference. Through extensive experiments, we demonstrate the effectiveness of ShallowJail, which substantially degrades the safety of state-of-the-art LLM responses. Our code is available at https://github.com/liuup/ShallowJail.

Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Placed in Jailbreaking, one of 12 directions in LLM safety and security. Builds on 41 of its 43 references that are in the map. First posted on arXiv 6 Feb 2026.

Builds on

41 of 43 references.

Closest ancestors · 18

Same direction, newest first

  1. 2025PII Jailbreaking in LLMs via Activation Steering Reveals Personal Information Leakage3 Jul
  2. 2025AdaSteer: Your Aligned LLM is Inherently an Adaptive Jailbreak Defender13 Apr
  3. 2025JBShield: Defending Large Language Models from Jailbreak Attacks through Activated Concept Analysis and Manipulation11 Feb
  4. 2025Understanding and Enhancing the Transferability of Jailbreaking Attacks5 Feb
  5. 2025Jailbreaking LLMs' Safeguard with Universal Magic Words for Text Embedding Models30 Jan
  6. 2024Token Highlighter: Inspecting and Mitigating Jailbreak Prompts for Large Language Models24 Dec
  7. 2024Emoji Attack: Enhancing Jailbreak Attacks Against Judge LLM Detection1 Nov
  8. 2024Towards Understanding Jailbreak Attacks in LLMs: A Representation Space Analysis16 Jun
  9. 2024Jailbreaking Leading Safety-Aligned LLMs with Simple Adaptive Attacks2 Apr
  10. 2024Gradient Cuff: Detecting Jailbreak Attacks on Large Language Models by Exploring Refusal Loss Landscapes1 Mar
  11. 2023Bypassing the Safety Training of Open-Source LLMs with Priming Attacks19 Dec
  12. 2023Tree of Attacks: Jailbreaking Black-Box LLMs Automatically4 Dec
6 more
  1. 2023Jailbreaking Black Box Large Language Models in Twenty Queries12 Oct
  2. 2023Catastrophic Jailbreak of Open-source LLMs via Exploiting Generation10 Oct
  3. 2023AutoDAN: Generating Stealthy Jailbreak Prompts on Aligned Large Language Models3 Oct
  4. 2023Detecting Language Model Attacks with Perplexity27 Aug
  5. 2023"Do Anything Now": Characterizing and Evaluating In-The-Wild Jailbreak Prompts on Large Language Models7 Aug
  6. 2023Universal and Transferable Adversarial Attacks on Aligned Language Models27 Jul

Other references · 23

  1. 2022Training language models to follow instructions with human feedbackcited by 15,712
  2. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,302
  3. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,355
  4. 2025DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learningcited by 6,146
  5. 2023Tree of Thoughts: Deliberate Problem Solving with Large Language Modelscited by 3,155
  6. 2023Llama Guard: LLM-based Input-Output Safeguard for Human-AI Conversationscited by 1,124
  7. 2022Red Teaming Language Models with Language Modelscited by 983
  8. 2023Steering Language Models With Activation Engineeringcited by 824
  9. 2024Safety Alignment Should Be Made More Than Just a Few Tokens Deepcited by 450
  10. 2024Improving Alignment and Robustness with Circuit Breakerscited by 302
  11. 2024ArtPrompt: ASCII Art-based Jailbreak Attacks against Aligned LLMscited by 197
  12. 2024Improving Instruction-Following in Language Models through Activation Steeringcited by 149
11 more
  1. 2023Inspecting and Editing Knowledge Representations in Language Modelscited by 140
  2. 2025Qwen3Guard Technical Reportcited by 125
  3. 2025AceReason-Nemotron: Advancing Math and Code Reasoning through Reinforcement Learningcited by 85
  4. 2024InferAligner: Inference-Time Alignment for Harmlessness through Cross-Model Guidancecited by 78
  5. 2025AlphaSteer: Learning Refusal Steering with Principled Null-Space Constraintcited by 45
  6. 2024Steering Away from Harm: An Adaptive Approach to Defending Vision Language Model Against Jailbreakscited by 44
  7. 2024Activation Scaling for Steering and Interpreting Language Modelscited by 33
  8. 2024Beyond Single Concept Vector: Modeling Concept Subspace in LLMs with Gaussian Distributioncited by 24
  9. 2024Steering Large Language Models between Code Execution and Textual Reasoningcited by 24
  10. 2024Context Steering: Controllable Personalization at Inference Timecited by 22
  11. 2025The Rogue Scalpel: Activation Steering Compromises LLM Safetycited by 18

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026Do Thinking Tokens Help with Safety?cited by 3