Challenge: Empirical evaluations on ML models show substantial reductions in unsafe generations and improved robustness against jailbreak attacks.
Approach: They propose a resource-efficient pruning framework that directly identifies unsafe behaviors while preserving model utility.
Outcome: The proposed framework reduces unsafe generations and improves robustness against jailbreak attacks with minimal utility loss.

Similar Papers

OASIS: Mitigating Harmful Fine-tuning Attacks on LLMs via Orthogonal and Adaptive Safety Alignment Strategy (2026.acl-long)

Copied to clipboard

Challenge: Existing methods to decouple safety enforcement from harmful feature acquisition rely on perturbation directions that conflict with harmful gradients . harmful fine-tuning attacks pose a significant challenge for service providers aiming to uphold rigorous safety standards.
Approach: They propose an orthogonal and ad hoc safety alignment strategy to decouple safety enforcement from harmful feature acquisition.
Outcome: Experiments on four large language models show that OASIS reduces the Harmful Score by 60% compared to baselines while maintaining stable task utility.
On the Vulnerability of Safety Alignment in Open-Access LLMs (2024.findings-acl)

Copied to clipboard

Challenge: Large language models (LLMs) are susceptible to malicious exploitation, but are often rejected and limited harmfulness is limited.
Approach: They propose two types of reverse alignment techniques: reverse supervised fine-tuning (RSFT) and reverse preference optimization (RPO).
Outcome: The proposed methods can significantly enhance the success rate and harmfulness of jailbreak attacks, but they face high rejection rates and limited harmfulness.
The Art of (Mis)alignment: How Fine-Tuning Methods Effectively Misalign and Realign LLMs in Post-Training (2026.findings-acl)

Copied to clipboard

Challenge: Misaligned large language models can magnify harm by exploiting them to undermine safety . et al., 2022b; Bai e.t., 2023): misalignment, realignment and model-specific resistance are important .
Approach: They evaluate four methods to identify a mechanism asymmetry between attack and defense . they find that ORPO is most effective for misalignment, but DPO excels in realignment .
Outcome: The proposed methods show a mechanism asymmetry between attack and defense . the proposed methods excel in realignment, but at the expense of model utility .
Layer-Aware Representation Filtering: Purifying Finetuning Data to Preserve LLM Safety Alignment (2025.emnlp-main)

Copied to clipboard

Challenge: Recent studies show that fine-tuning with benign data can compromise safety of aligned LLMs.
Approach: They propose a Layer-Aware Representation Filtering method that detects safety-degrading layers within the LLM and leverages their representations to detect them.
Outcome: The proposed method can detect safety-degrading features in benign data and remove them from the model.
SafeMERGE: Preserving Safety Alignment in Fine-Tuned Large Language Models via Selective Layer-Wise Model Merging (2026.findings-acl)

Copied to clipboard

Challenge: Recent studies show that fine-tuning can erode safety alignment, causing LLMs to respond to harmful or unethical prompts.
Approach: They propose a lightweight framework that restores safety while maintaining downstream performance.
Outcome: The proposed framework reduces harmful outputs compared to other defenses, with negligible impact on utility.
SafeQuant: LLM Safety Analysis via Quantized Gradient Inspection (2025.naacl-long)

Copied to clipboard

Challenge: Existing approaches to jailbreak Large Language Models (LLMs) use computationally intensive verification or require adversarial fine-tuning, leaving models vulnerable to advanced attacks.
Approach: They propose a framework that leverages quantized gradient patterns to identify harmful prompts efficiently.
Outcome: The proposed framework outperforms existing defenses across multiple benchmarks while maintaining model utility.
PURE: Aligning LLM via Pluggable Query Reformulation for Enhanced Helpfulness (2024.findings-emnlp)

Copied to clipboard

Challenge: Large language models (LLMs) depend on vast amounts of text data sourced from the Internet for their training.
Approach: They propose a new alignment paradigm that reformulates risky queries into highly relevant yet harmless ones before feeding them into LLMs.
Outcome: The proposed approach eliminates the high costs of training base LLMs and achieves a promising balance of harmlessness and helpfulness.
SecDecoding: Steerable Decoding for Safer LLM Generation (2025.findings-emnlp)

Copied to clipboard

Challenge: Existing decoding-time defense methods suffer from limited generalization, high computational overhead, or significant utility degradation.
Approach: They propose a decoding-time defense framework that leverages a pair of small contrastive models to estimate token-level safety signals by measuring divergence in their output distributions.
Outcome: The proposed framework achieves near-zero attack success rates against a wide spectrum of advanced jailbreak attacks while maintaining the model’s helpfulness with minimal degradation.
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.
Calibrating Inference Time Alignment with Sequence-level Risk Accumulation (2026.acl-long)

Copied to clipboard

Challenge: Existing approaches to decode large language models (LLMs) often over-reject benign information, limiting their generalizability in real-world scenarios where harmful and benign information coexist.
Approach: They propose a framework to regulate decoding alignments for Large Language Models (LLMs) they employ a reward-guided branch decoding paradigm to incorporate safety awareness during generation.
Outcome: The proposed framework achieves superior performance on four attack benchmarks and two neutral datasets.

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