Differences
This shows you the differences between two versions of the page.
| Both sides previous revision Previous revision Next revision | Previous revision | ||
|
class:gradsec2026 [2026/05/15 08:58] hanwoo [Agenda] |
class:gradsec2026 [2026/06/15 11:25] (current) hanwoo [Agenda] |
||
|---|---|---|---|
| Line 37: | Line 37: | ||
| | ::: | Jo | [[https://www.usenix.org/system/files/sec21-schuster.pdf|You autocomplete me: Poisoning vulnerabilities in neural code completion]] | {{ :class:인공지능보안_03_11_조현준.pptx |}} | | | | ::: | Jo | [[https://www.usenix.org/system/files/sec21-schuster.pdf|You autocomplete me: Poisoning vulnerabilities in neural code completion]] | {{ :class:인공지능보안_03_11_조현준.pptx |}} | | | ||
| | 3/18 | Minho | | | | | | 3/18 | Minho | | | | | ||
| - | | ::: | Han | [[https://arxiv.org/pdf/2102.07995.pdf|D2a: A dataset built for ai-based vulnerability detection methods using differential analysis]] | {{ :class:d2a.pptx |}} | | | | + | | ::: | Han | [[https://arxiv.org/pdf/2102.07995.pdf|D2a: A dataset built for ai-based vulnerability detection methods using differential analysis]] | {{ :class:d2a.pptx |}} | | |
| | 3/27 | Minho | | | | | | 3/27 | Minho | | | | | ||
| | ::: | Kwak| [[https://www.mdpi.com/1424-8220/23/9/4403/pdf|A Deep Learning-Based Innovative Technique for Phishing Detection with URLs]] | {{ :class:현대_보안에서_url을_이용한_피싱_탐지를_위한_딥러닝_기반_혁신_기법.pdf |}} | | | | ::: | Kwak| [[https://www.mdpi.com/1424-8220/23/9/4403/pdf|A Deep Learning-Based Innovative Technique for Phishing Detection with URLs]] | {{ :class:현대_보안에서_url을_이용한_피싱_탐지를_위한_딥러닝_기반_혁신_기법.pdf |}} | | | ||
| Line 44: | Line 44: | ||
| Learning for Malware Detection in Executables]] |{{ :class:dl_for_malware_detection_in_ex_인공지능보안_조현준.pptx |}} | | | Learning for Malware Detection in Executables]] |{{ :class:dl_for_malware_detection_in_ex_인공지능보안_조현준.pptx |}} | | | ||
| | 4/15 | Han | [[https://arxiv.org/pdf/1904.12843|Adversarial Training for Free!]] |{{ :class:adversarial_training_for_free_.pdf |}} | | | | 4/15 | Han | [[https://arxiv.org/pdf/1904.12843|Adversarial Training for Free!]] |{{ :class:adversarial_training_for_free_.pdf |}} | | | ||
| - | | ::: | Minho | LLM | {{ :class:ai-introduction.pdf |}} | | + | | ::: | Minho | LLM | {{ :class:ai-introduction.pdf |}} | | |
| | 4/24 | No class | | | | | | 4/24 | No class | | | | | ||
| | 4/29 | Kwak | Deep reinforcement learning for time series:playing idealized trading games |{{ :class:시계열_데이터를_이용한_강화학습_기반_이상화된_트레이딩_.pdf |}} | | | | 4/29 | Kwak | Deep reinforcement learning for time series:playing idealized trading games |{{ :class:시계열_데이터를_이용한_강화학습_기반_이상화된_트레이딩_.pdf |}} | | | ||
| Line 51: | Line 51: | ||
| | ::: | Han | [[https://arxiv.org/pdf/2305.00944|Poisoning Language Models During Instruction Tuning]] | {{ :class:poisoning_language_models_during_instruction_tuning.pdf|poisoning_language_models_during_instruction_tuning}} | | | | ::: | Han | [[https://arxiv.org/pdf/2305.00944|Poisoning Language Models During Instruction Tuning]] | {{ :class:poisoning_language_models_during_instruction_tuning.pdf|poisoning_language_models_during_instruction_tuning}} | | | ||
| | 5/13 | Han | [[https://arxiv.org/pdf/2004.04692 |RETHINKING THE TRIGGER OF BACKDOOR ATTACK]] | {{ :class:rethinking_the_trigger_of_backdoor_attack.pdf |rethinking_the_trigger_of_backdoor_attack}} | | | | 5/13 | Han | [[https://arxiv.org/pdf/2004.04692 |RETHINKING THE TRIGGER OF BACKDOOR ATTACK]] | {{ :class:rethinking_the_trigger_of_backdoor_attack.pdf |rethinking_the_trigger_of_backdoor_attack}} | | | ||
| - | | ::: | Kwak | | | | | + | | ::: | Kwak | [[https://arxiv.org/pdf/1910.00033 |Hidden Trigger Backdoor Attacks]] | {{ :class:hidden_trigger_backdoor_attacks.pdf |}} | | |
| - | | 5/20 | Kwak | | | | | + | | 5/20 | Kwak | [[https://arxiv.org/pdf/2012.07805 |Extracting Training Data from Large Language Models]] | {{ :class:extracting_training_data_from_large_language_models_2_.pdf|pdf}} | | |
| - | | ::: | Jo | | | | | + | | ::: | Jo | [[https://www.ndss-symposium.org/wp-content/uploads/2026-f797-paper.pdf]] |{{ :class:발표자료_조현준.pptx |}}| | |
| | 5/27 | Jo | | | | | | 5/27 | Jo | | | | | ||
| - | | ::: | Han | | | | | + | | ::: | Han | [[https://arxiv.org/pdf/2307.02483.pdf|Jailbroken-How Does LLM Safety Training Fail]] | {{ :class:jailbroken-how_does_llm_safety_training_fail.pdf |발표자료}} | | |
| - | | 6/5 | Kwak | | | | | + | | 6/5 | Kwak | [[https://arxiv.org/pdf/2010.08138.pdf|Input-Aware Dynamic Backdoor Attack ]] | {{ :class:input-aware_dynamic_backdoor_attack.pdf |}} | | |
| | 6/10 | No Class | | | | | | 6/10 | No Class | | | | | ||
| ====== Class Information ====== | ====== Class Information ====== | ||
| Line 162: | Line 162: | ||
| * Keywords: Physical adversarial examples, backdoor attacks, computer vision, robust perturbations, physical-world attacks | * Keywords: Physical adversarial examples, backdoor attacks, computer vision, robust perturbations, physical-world attacks | ||
| * URL: https://arxiv.org/pdf/2004.04692.pdf | * URL: https://arxiv.org/pdf/2004.04692.pdf | ||
| - | - **Hidden Trigger Backdoor Attacks** | + | - <fc red>(kawk)</fc> **Hidden Trigger Backdoor Attacks** |
| * Aniruddha Saha et al., AAAI 2020 | Pages: 8 | Difficulty: 3/5 | * Aniruddha Saha et al., AAAI 2020 | Pages: 8 | Difficulty: 3/5 | ||
| * Abstract: Proposes backdoor attacks where triggers are hidden in the neural network's feature space rather than being visible patterns in the input. These attacks are harder to detect because there's no visible trigger pattern that can be identified through input inspection or trigger inversion techniques. | * Abstract: Proposes backdoor attacks where triggers are hidden in the neural network's feature space rather than being visible patterns in the input. These attacks are harder to detect because there's no visible trigger pattern that can be identified through input inspection or trigger inversion techniques. | ||
| Line 179: | Line 179: | ||
| ==== C3. Privacy Attacks on Machine Learning ==== | ==== C3. Privacy Attacks on Machine Learning ==== | ||
| - | - **Extracting Training Data from Large Language Models** | + | -<fc red>(kawk)</fc> **Extracting Training Data from Large Language Models** |
| * Nicholas Carlini et al., USENIX Security 2021 | Pages: 17 | Difficulty: 3/5 | * Nicholas Carlini et al., USENIX Security 2021 | Pages: 17 | Difficulty: 3/5 | ||
| * Abstract: Demonstrates that large language models like GPT-2 memorize and can be made to emit verbatim training data including personal information, phone numbers, and copyrighted content. The paper raises serious privacy concerns for LLMs trained on web data and shows that model size correlates with memorization capability. | * Abstract: Demonstrates that large language models like GPT-2 memorize and can be made to emit verbatim training data including personal information, phone numbers, and copyrighted content. The paper raises serious privacy concerns for LLMs trained on web data and shows that model size correlates with memorization capability. | ||
| Line 213: | Line 213: | ||
| ==== C4. LLM Security & Jailbreaking ==== | ==== C4. LLM Security & Jailbreaking ==== | ||
| - | - **Jailbroken: How Does LLM Safety Training Fail?** | + | - <fc red>(Han)</fc> **Jailbroken: How Does LLM Safety Training Fail?** |
| * Alexander Wei et al., NeurIPS 2023 | Pages: 34 | Difficulty: 3/5 | * Alexander Wei et al., NeurIPS 2023 | Pages: 34 | Difficulty: 3/5 | ||
| * Abstract: Analyzes why safety training in LLMs can be circumvented through jailbreaking. Identifies two fundamental failure modes: competing objectives during training and mismatched generalization between safety and capabilities. Provides theoretical framework for understanding jailbreak vulnerabilities and suggests that current alignment approaches have inherent limitations. | * Abstract: Analyzes why safety training in LLMs can be circumvented through jailbreaking. Identifies two fundamental failure modes: competing objectives during training and mismatched generalization between safety and capabilities. Provides theoretical framework for understanding jailbreak vulnerabilities and suggests that current alignment approaches have inherent limitations. | ||
class/gradsec2026.1778810298.txt.gz · Last modified: 2026/05/15 08:58 by hanwoo · [Old revisions]
