Challenge: Safety-aligned LLMs respond to prompts with compliance or refusal, each corresponding to distinct directions in the model’s activation space.
Approach: They propose an initialization framework that aims to project unseen prompts further along compliance directions.
Outcome: The proposed initialization framework achieves an increased attack success rate and reduced computational overhead, highlighting the fragility of safety-aligned LLMs.

Similar Papers

Beyond Surface Alignment: Rebuilding LLMs Safety Mechanism via Probabilistically Ablating Refusal Direction (2025.findings-emnlp)

Copied to clipboard

Challenge: Jailbreak attacks pose persistent threats to large language models . current safety alignment methods have insufficient safety alignment depth and unrobust internal defense mechanisms.
Approach: a new safety alignment framework is developed to overcome jailbreak attacks . the framework forces the model to dynamically rebuild its refusal mechanisms from jailbreak states .
Outcome: a new safety alignment framework reduces attack success rates by approximately 95% on four open-source LLM families and six representative attacks.
Guiding not Forcing: Enhancing the Transferability of Jailbreaking Attacks on LLMs via Removing Superfluous Constraints (2025.acl-long)

Copied to clipboard

Challenge: Jailbreaking attacks can effectively induce unsafe behaviors in Large Language Models (LLMs).
Approach: They propose a conceptual framework to elucidate transferability of gradient-based jailbreaking methods . they identify superfluous constraints as significant barriers to improved transferability .
Outcome: The proposed method increases the overall transfer attack success rate (T-ASR) across target and source models with varying safety levels from 18.4% to 50.3% while improving stability and controllability of jailbreak behaviors.
Jailbreak LLMs through Internal Stance Manipulation (2025.emnlp-main)

Copied to clipboard

Challenge: Existing approaches to exploit LLMs' inherent safety mechanism, including GCG and AutoDAN, are ineffective for certain malicious requests.
Approach: They propose a method that generates jailbreak prompts to suppress a refusal stance and induce affirmative responses by modifying adversarial prompts.
Outcome: The proposed method outperforms the best baseline approach in Llama-2-7b-chat and achieves a 92.2% success rate across all models.
Activation-Guided Local Editing for Jailbreaking Attacks (2026.acl-long)

Copied to clipboard

Challenge: Existing methods for jailbreaking Large Language Models (LLMs) are limited and produce incoherent or unreadable inputs.
Approach: They propose a two-stage framework that performs a one-shot, scenario-based generation of context and rephrases the original malicious query to obscure its harmful intent.
Outcome: The proposed framework achieves state-of-the-art Attack Success Rate, with gains of up to 37.74% over the strongest baseline, and excellent transferability to black-box and large-scale models.
Compiling Activation Steering into Weights via Null-Space Constraints for Stealthy Backdoors (2026.acl-long)

Copied to clipboard

Challenge: Existing methods to inject safety-aligned large language models rely on token-level mappings, which do not guarantee sustained harmful output.
Approach: They propose a method that directly modifies model weights to map a trigger to an attacker-specified response.
Outcome: The proposed method achieves high triggered attack success while maintaining non-triggered safety and general utility.
Shaping the Safety Boundaries: Understanding and Defending Against Jailbreaks in Large Language Models (2025.acl-long)

Copied to clipboard

Challenge: Understanding how jailbreaking works remains limited, hindering the development of effective defense strategies.
Approach: They propose a new mechanism that adaptively constrains activations within the safety boundary and propose 'Activation Boundary Defense' to enhance its effectiveness.
Outcome: The proposed defense achieves an average Defense Success Rate (DSR) of over 98% against various jailbreak attacks, with less than 2% impact on the model’s general capabilities.
Intention Analysis Makes LLMs A Good Jailbreak Defender (2025.coling-main)

Copied to clipboard

Challenge: Existing methods to align large language models with human values overlook the intrinsic nature of jailbreaks, which limits their effectiveness in complex scenarios.
Approach: They propose a simple yet highly effective defense strategy, i.e., Intention Analysis (IA). They show that IA suppresses LLM’s tendency to follow jailbreak prompts, thereby enhancing safety.
Outcome: The proposed strategy reduces harmfulness of LLMs and outperforms GPT-3.5 in attack success rate.
Jailbreaks as Inference-Time Alignment: A Framework for Understanding Safety Failures in LLMs (2026.eacl-long)

Copied to clipboard

Challenge: Large language models are safety-aligned to prevent harmful response generation . prior work on jailbreak effectiveness has focused on analyzing success rate of jailbreaks .
Approach: They propose to frame jailbreaks as inference-time alignment and draw suboptimal bounds . they also propose a Safety-Net to measure how vulnerable an LLM is to jailbreak attacks .
Outcome: a new framework allows researchers to show how vulnerable an LLM is to jailbreaks . a Safety-Net measures how vulnerable the model is to attacks, the authors say .
Analysing the Safety Pitfalls of Steering Vectors (2026.findings-acl)

Copied to clipboard

Challenge: Activation steering has emerged as a powerful tool to shape LLM behaviour without the need for weight updates.
Approach: They propose to audit steering vectors obtained with Contrastive Activation Addition (CAA) and propose a mechanistic explanation for this finding.
Outcome: The proposed approach significantly improves the success rate of jailbreak attacks, with stronger amplification under simple template-based attacks.
How Jailbreak Defenses Work and Ensemble? A Mechanistic Investigation (2025.findings-emnlp)

Copied to clipboard

Challenge: Jailbreak attacks, where harmful prompts bypass generative models’ built-in safety, raise serious concerns about model vulnerability.
Approach: They propose to reframe the standard generation task as a binary classification problem to assess model refusal tendencies for both harmful and benign queries.
Outcome: The proposed defenses improve model safety or optimize the trade-off between safety and helpfulness.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations