CacheTrap: Unveiling a Stealthier Gray-Box Trojan against LLMs
Fuente:
arXiv
Saved in:
| Main Authors: | Nahian, Mohaiminul Al, Almalky, Abeer Matar A., Aragonda, Gamana, Zhou, Ranyang, Ahmed, Sabbir, Ponomarev, Dmitry, Yang, Li, Angizi, Shaahin, Rakin, Adnan Siraj |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Similar Items
EIM-TRNG: Obfuscating Deep Neural Network Weights with Encoding-in-Memory True Random Number Generator via RowHammer
by: Zhou, Ranyang, et al.
Published: (2025)
by: Zhou, Ranyang, et al.
Published: (2025)
Invisible Hands: Gray-Box Bit Flip Attack for Steering LLMs Without Knowledge of Gradients, Data, and Weights
by: Almalky, Abeer Matar A., et al.
Published: (2025)
by: Almalky, Abeer Matar A., et al.
Published: (2025)
DNN-Defender: A Victim-Focused In-DRAM Defense Mechanism for Taming Adversarial Weight Attack on DNNs
by: Zhou, Ranyang, et al.
Published: (2023)
by: Zhou, Ranyang, et al.
Published: (2023)
Compromising the Intelligence of Modern DNNs: On the Effectiveness of Targeted RowPress
by: Zhou, Ranyang, et al.
Published: (2024)
by: Zhou, Ranyang, et al.
Published: (2024)
DRAM-Profiler: An Experimental DRAM RowHammer Vulnerability Profiling Mechanism
by: Zhou, Ranyang, et al.
Published: (2024)
by: Zhou, Ranyang, et al.
Published: (2024)
Robo-Troj: Attacking LLM-based Task Planners
by: Nahian, Mohaiminul Al, et al.
Published: (2025)
by: Nahian, Mohaiminul Al, et al.
Published: (2025)
PROTEA: Securing Robot Task Planning and Execution
by: Altaweel, Zainab, et al.
Published: (2026)
by: Altaweel, Zainab, et al.
Published: (2026)
Unified Alignment Protocol: Making Sense of the Unlabeled Data in New Domains
by: Ahmed, Sabbir, et al.
Published: (2025)
by: Ahmed, Sabbir, et al.
Published: (2025)
Fisher Information guided Purification against Backdoor Attacks
by: Karim, Nazmul, et al.
Published: (2024)
by: Karim, Nazmul, et al.
Published: (2024)
Dependability in Embedded Systems: A Survey of Fault Tolerance Methods and Software-Based Mitigation Techniques
by: Solouki, Mohammadreza Amel, et al.
Published: (2024)
by: Solouki, Mohammadreza Amel, et al.
Published: (2024)
SPICEPilot: Navigating SPICE Code Generation and Simulation with AI Guidance
by: Vungarala, Deepak, et al.
Published: (2024)
by: Vungarala, Deepak, et al.
Published: (2024)
Magnetisation moment of a bounded 3D sample: asymptotic recovery from planar measurements on a large disk
by: Ponomarev, Dmitry
Published: (2022)
by: Ponomarev, Dmitry
Published: (2022)
A Method to Extrapolate the Data for the Inverse Magnetisation Problem with a Planar Sample
by: Ponomarev, Dmitry
Published: (2024)
by: Ponomarev, Dmitry
Published: (2024)
Chiral higher-spin double copy
by: Ponomarev, Dmitry
Published: (2024)
by: Ponomarev, Dmitry
Published: (2024)
Certifiable Safe RLHF: Fixed-Penalty Constraint Optimization for Safer Language Models
by: Pandit, Kartik, et al.
Published: (2025)
by: Pandit, Kartik, et al.
Published: (2025)
HiRISE: High-Resolution Image Scaling for Edge ML via In-Sensor Compression and Selective ROI
by: Reidy, Brendan, et al.
Published: (2024)
by: Reidy, Brendan, et al.
Published: (2024)
Inconsistency of point-particle dynamics on higher-spin backgrounds
by: Ivanovskiy, Vyacheslav, et al.
Published: (2025)
by: Ivanovskiy, Vyacheslav, et al.
Published: (2025)
Manifest color-kinematics duality for point particles interacting with self-dual fields
by: Ivanovskiy, Vyacheslav, et al.
Published: (2024)
by: Ivanovskiy, Vyacheslav, et al.
Published: (2024)
Inconsistency of point-particle dynamics on higher-spin backgrounds: massive particles
by: Ivanovskiy, Vyacheslav, et al.
Published: (2025)
by: Ivanovskiy, Vyacheslav, et al.
Published: (2025)
Exploiting Boosting in Hyperdimensional Computing for Enhanced Reliability in Healthcare
by: Jeong, SungHeon, et al.
Published: (2024)
by: Jeong, SungHeon, et al.
Published: (2024)
SA-DS: A Dataset for Large Language Model-Driven AI Accelerator Design Generation
by: Vungarala, Deepak, et al.
Published: (2024)
by: Vungarala, Deepak, et al.
Published: (2024)
FedChip: Federated LLM for Artificial Intelligence Accelerator Chip Design
by: Nazzal, Mahmoud, et al.
Published: (2025)
by: Nazzal, Mahmoud, et al.
Published: (2025)
Self-dual classical higher-spin multicopy
by: Misuna, Nikita, et al.
Published: (2026)
by: Misuna, Nikita, et al.
Published: (2026)
Beyond Jailbreaks: Revealing Stealthier and Broader LLM Security Risks Stemming from Alignment Failures
by: Zhou, Yukai, et al.
Published: (2025)
by: Zhou, Yukai, et al.
Published: (2025)
Film Farbe Fläche.
by: Rakin, Jelena
Published: (2021)
by: Rakin, Jelena
Published: (2021)
GLANCE: Gaze-Led Attention Network for Compressed Edge-inference
by: Solanki, Neeraj, et al.
Published: (2026)
by: Solanki, Neeraj, et al.
Published: (2026)
TPU-Gen: LLM-Driven Custom Tensor Processing Unit Generator
by: Vungarala, Deepak, et al.
Published: (2025)
by: Vungarala, Deepak, et al.
Published: (2025)
Gray-Box Fuzzing in Local Space
by: Jonáš, Martin, et al.
Published: (2025)
by: Jonáš, Martin, et al.
Published: (2025)
LIMCA: LLM for Automating Analog In-Memory Computing Architecture Design Exploration
by: Vungarala, Deepak, et al.
Published: (2025)
by: Vungarala, Deepak, et al.
Published: (2025)
Light-Bound Transformers: Hardware-Anchored Robustness for Silicon-Photonic Computer Vision Systems
by: Chen, Xuming, et al.
Published: (2026)
by: Chen, Xuming, et al.
Published: (2026)
Lightator: An Optical Near-Sensor Accelerator with Compressive Acquisition Enabling Versatile Image Processing
by: Morsali, Mehrdad, et al.
Published: (2024)
by: Morsali, Mehrdad, et al.
Published: (2024)
Low dimensional fragment-based descriptors for property predictions in inorganic materials with machine learning
by: Islam, Md Mohaiminul
Published: (2024)
by: Islam, Md Mohaiminul
Published: (2024)
On the limiting amplitude principle for the wave equation with variable coefficients
by: Arnold, Anton, et al.
Published: (2022)
by: Arnold, Anton, et al.
Published: (2022)
Unveiling the Synergistic Influence of TiO2 and Chitosan‐Based Hydrogel in Precision Surface Co‐Modification for Superior Pure Titanium Implant Performance
by: Shaahin Mohammadzadeh Asl, et al.
Published: (2025)
by: Shaahin Mohammadzadeh Asl, et al.
Published: (2025)
HyperSense: Hyperdimensional Intelligent Sensing for Energy-Efficient Sparse Data Processing
by: Yun, Sanggeon, et al.
Published: (2024)
by: Yun, Sanggeon, et al.
Published: (2024)
HyperSense: Hyperdimensional Intelligent Sensing for Energy‐Efficient Sparse Data Processing
by: Sanggeon Yun, et al.
Published: (2024)
by: Sanggeon Yun, et al.
Published: (2024)
Gray-Box Poisoning of Continuous Malware Ingestion Pipelines
by: Dolejš, Jan, et al.
Published: (2026)
by: Dolejš, Jan, et al.
Published: (2026)
Opto-ViT: Architecting a Near-Sensor Region of Interest-Aware Vision Transformer Accelerator with Silicon Photonics
by: Morsali, Mehrdad, et al.
Published: (2025)
by: Morsali, Mehrdad, et al.
Published: (2025)
Neuro-Photonix: Enabling Near-Sensor Neuro-Symbolic AI Computing on Silicon Photonics Substrate
by: Najafi, Deniz, et al.
Published: (2024)
by: Najafi, Deniz, et al.
Published: (2024)
TrojanTO: Action-Level Backdoor Attacks against Trajectory Optimization Models
by: Dai, Yang, et al.
Published: (2025)
by: Dai, Yang, et al.
Published: (2025)
Similar Items
-
EIM-TRNG: Obfuscating Deep Neural Network Weights with Encoding-in-Memory True Random Number Generator via RowHammer
by: Zhou, Ranyang, et al.
Published: (2025) -
Invisible Hands: Gray-Box Bit Flip Attack for Steering LLMs Without Knowledge of Gradients, Data, and Weights
by: Almalky, Abeer Matar A., et al.
Published: (2025) -
DNN-Defender: A Victim-Focused In-DRAM Defense Mechanism for Taming Adversarial Weight Attack on DNNs
by: Zhou, Ranyang, et al.
Published: (2023) -
Compromising the Intelligence of Modern DNNs: On the Effectiveness of Targeted RowPress
by: Zhou, Ranyang, et al.
Published: (2024) -
DRAM-Profiler: An Experimental DRAM RowHammer Vulnerability Profiling Mechanism
by: Zhou, Ranyang, et al.
Published: (2024)